© 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. 96534
    Prev
    Next
    INDEX
    Explanations

    Code, dates, non-English characters

    np_max-act-logits · gemini-2.0-flash
    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
     spelling
    -0.29
     troop
    -0.27
    èī²
    -0.27
    åĩ¿
    -0.27
    éĹ´è·Ŀ
    -0.26
    æ»Ł
    -0.26
    èī²å½©
    -0.25
    pling
    -0.25
    -prefix
    -0.25
    _patterns
    -0.25
    POSITIVE LOGITS
    çĶ¨æīĭ
    0.28
    ATOR
    0.28
    åѦä½į
    0.27
    鸱
    0.26
    -looking
    0.26
    ç«ŀéĢī
    0.26
    æ¶Ī
    0.26
     synerg
    0.25
    çŀĦ
    0.25
    è¯Ħ论
    0.24
    Activations Density 0.882%

    No Known Activations