© 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. 108257
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    建档
    -0.26
    ëĤ©
    -0.26
    irie
    -0.25
     ref
    -0.24
     void
    -0.24
    没æľīåĬŀæ³ķ
    -0.24
     conj
    -0.23
    /umd
    -0.23
    è¥ŀ
    -0.23
    ibbon
    -0.23
    POSITIVE LOGITS
    å©´
    0.29
    è¡ĮæĿİ
    0.26
    积
    0.26
    XE
    0.25
    acas
    0.25
    è§Ĩéĩİ
    0.24
    IE
    0.24
    è¿ŀç»Ń
    0.24
    imes
    0.23
     Poster
    0.23
    Activations Density 7.404%

    No Known Activations

    This feature has no known activations.