© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38875
    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
    åĪ¶åīĤ
    -0.32
    åĨľ
    -0.27
    sembling
    -0.27
    åħ¨æĹ¥åĪ¶
    -0.27
    0
    -0.26
    --
    -0.26
     outcome
    -0.26
    ç»ĵå±Ģ
    -0.26
    ultimate
    -0.26
    +
    -0.26
    POSITIVE LOGITS
    æĬ½è±¡
    0.31
    åĪĩæį¢
    0.28
     Ïĥ
    0.27
    ä¸Ģå¹ķ
    0.26
    æ¸ħæĻ°
    0.25
     porr
    0.25
    .lab
    0.25
    bau
    0.24
    .opend
    0.24
     Liqu
    0.24
    Activations Density 1.059%

    No Known Activations

    This feature has no known activations.