© 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. 40657
    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
     Fits
    -0.32
    benh
    -0.29
    uraa
    -0.29
    mv
    -0.28
    zcze
    -0.28
    ä¾Ķ
    -0.27
    _mv
    -0.27
    -Pack
    -0.26
    fäh
    -0.26
    bens
    -0.25
    POSITIVE LOGITS
    ↵
    0.36
    B
    0.34
    A
    0.32
    ...↵
    0.31
    1
    0.30
    P
    0.29
    Definition
    0.29
    .
    0.29
    ...
    0.29
    åĺ¤
    0.29
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.