© 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. 38957
    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
     unknown
    -0.27
     Zodiac
    -0.26
     ger
    -0.26
     even
    -0.25
     ir
    -0.25
     puls
    -0.25
     Wish
    -0.25
    大æĪ·
    -0.25
    .GetAsync
    -0.25
     fluct
    -0.25
    POSITIVE LOGITS
    建
    0.27
    æ³Ľ
    0.26
    åĢŁéī´
    0.26
    éĿ¢æĿ¿
    0.26
    æŀ¶
    0.26
    éĹ´è·Ŀ
    0.26
    IBC
    0.25
    ÑĢок
    0.25
    社
    0.25
    tributes
    0.25
    Activations Density 1.857%

    No Known Activations

    This feature has no known activations.