© 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. 40027
    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
    ä¸įåľ¨
    -0.29
    æķ·
    -0.29
    /off
    -0.29
    าà¸ĩ
    -0.29
    ,âĢ¦↵↵
    -0.28
    <th
    -0.27
    å°ıå¿ĥ
    -0.27
    æĿ¾
    -0.26
    енÑĮ
    -0.26
    åĵij
    -0.26
    POSITIVE LOGITS
     Famous
    0.27
     hy
    0.26
     ден
    0.25
    ulan
    0.25
    isen
    0.25
     Ðijо
    0.25
    idents
    0.24
     Classified
    0.24
    _named
    0.24
     SplashScreen
    0.24
    Activations Density 1.807%

    No Known Activations

    This feature has no known activations.