© 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. 20-TRANSCODER-HP
    7. 130179
    Prev
    Next
    INDEX
    Explanations

    Punctuation/Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stitutions
    -0.28
     Yok
    -0.26
    comed
    -0.26
    俶
    -0.25
    æĻ¨æĬ¥
    -0.25
    íĦ¸
    -0.25
    orado
    -0.25
    mers
    -0.25
    odable
    -0.24
    å¾ķ
    -0.24
    POSITIVE LOGITS
     features
    0.35
     feature
    0.34
    åĬ²
    0.29
    éģĵ
    0.27
    é¢Ĩ导ä¸ĭ
    0.27
     separate
    0.26
    CellStyle
    0.26
     individual
    0.26
    ug
    0.26
    _feature
    0.26
    Activations Density 16.423%

    No Known Activations