© 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. 40773
    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
    indows
    -0.28
    leans
    -0.27
    manda
    -0.27
    ÑĥÑĩа
    -0.26
    QUIRE
    -0.26
    harma
    -0.26
    mando
    -0.26
    ispens
    -0.25
    inate
    -0.24
    <pre
    -0.24
    POSITIVE LOGITS
     I
    0.26
    Extras
    0.24
    eb
    0.24
     plot
    0.24
     i
    0.24
     downward
    0.23
    举ä¾ĭ
    0.23
     Down
    0.23
     Extras
    0.23
     wall
    0.23
    Activations Density 26.868%

    No Known Activations

    This feature has no known activations.