© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96026
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    np_max-act-logits · gemini-2.0-flash

    dates (numerical values representing years, days, or months) in the text.

    oai_token-act-pair · deepseek-v3Triggered by @finnwit

    Segments separated from contextual prose, often headlines, section breaks, or standalone statements.

    eleuther_acts_top20 · deepseek-v3Triggered by @finnwit
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.31
    ↵   ↵
    -0.28
    ↵	↵
    -0.28
    Intialized
    -0.28
    UsageId
    -0.27
     ?.
    -0.27
    ï¼ĮãĢĬ
    -0.27
     (__
    -0.26
    ↵     ↵
    -0.26
     cord
    -0.26
    POSITIVE LOGITS
    The
    0.44
    s
    0.42
    A
    0.40
    Another
    0.39
    This
    0.36
    “
    0.35
    H
    0.35
    M
    0.34
    If
    0.34
    """↵↵
    0.34
    Activations Density 5.698%

    No Known Activations