© 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. 38757
    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
    Negative Logits
    åĴĮæĶ¯æĮģ
    -0.30
    为客æĪ·
    -0.29
    åľ¨çݩ家
    -0.29
     unavoid
    -0.28
     anale
    -0.28
    æĹ¥æ¶Īæģ¯
    -0.27
    already
    -0.27
    ilver
    -0.27
     psychologically
    -0.27
     Horde
    -0.26
    POSITIVE LOGITS
     Pl
    0.34
     Old
    0.30
     old
    0.28
     Cap
    0.28
     Ba
    0.27
     Br
    0.27
     Se
    0.27
     Ap
    0.27
     Tr
    0.27
     Kap
    0.27
    Activations Density 12.812%

    No Known Activations

    This feature has no known activations.