© 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. 38800
    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
    entially
    -0.29
     trash
    -0.25
    è¡·
    -0.25
    /Gate
    -0.24
    otros
    -0.24
    lyn
    -0.24
    pragma
    -0.24
    å°ıå¿ĥ
    -0.24
    æķ´ä¸ª
    -0.23
    ç³Ł
    -0.23
    POSITIVE LOGITS
    大èĦij
    0.28
     proportions
    0.27
    ’,
    0.27
    ,’’
    0.26
    ’.
    0.25
    .Ass
    0.24
    ,’
    0.24
    UCH
    0.24
    umping
    0.23
    »,
    0.23
    Activations Density 38.368%

    No Known Activations

    This feature has no known activations.