© 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. 31-TRANSCODER-HP
    7. 19234
    Prev
    Next
    INDEX
    Explanations

    code and filenames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ¸
    -0.29
    çķĻè¨ĢæĿ¿
    -0.28
    \common
    -0.26
    sted
    -0.26
    lops
    -0.25
    charging
    -0.25
    overs
    -0.25
    amo
    -0.25
    ç»ĻåĬĽ
    -0.25
    amel
    -0.25
    POSITIVE LOGITS
    åŁĻ
    0.28
     fin
    0.27
     susp
    0.26
    екÑĤоÑĢ
    0.26
     Fin
    0.26
    纪å¾ĭ
    0.26
    unning
    0.26
    åĭĥ
    0.26
     BA
    0.26
    -ng
    0.25
    Activations Density 0.007%

    No Known Activations