© 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. 35-TRANSCODER-HP
    7. 40150
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥ½åĬĽå¼º
    -0.28
    olt
    -0.28
    slides
    -0.26
    å¢Ļ
    -0.26
    suit
    -0.26
    charts
    -0.26
    beck
    -0.26
    çīĨ
    -0.25
    plans
    -0.25
    uchen
    -0.24
    POSITIVE LOGITS
     longitudinal
    0.24
    -fr
    0.24
    窣
    0.24
    ä¸İæѤ
    0.23
     liter
    0.23
    第ä¸ĢæĿ¡
    0.23
    fäll
    0.23
    äºĮåŃĹ
    0.23
    ä»ĸ说
    0.23
     **************************************************************************
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.