© 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. 40703
    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
     stocking
    -0.28
    ionate
    -0.28
    enaries
    -0.27
    -death
    -0.27
    licant
    -0.27
    å£ķ
    -0.27
    Cumh
    -0.27
    rious
    -0.26
    -demand
    -0.26
    ocos
    -0.26
    POSITIVE LOGITS
     -
    0.35
     (
    0.35
     <
    0.35
     *
    0.34
     ...
    0.34
    0.33
     ->
    0.33
     ·
    0.33
     com
    0.32
    (s
    0.32
    Activations Density 0.330%

    No Known Activations

    This feature has no known activations.