© 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. 40763
    Prev
    Next
    INDEX
    Explanations

    List choices

    np_max-act-logits · gemini-2.0-flash
    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
     natural
    -0.39
     spatial
    -0.36
     elemental
    -0.35
     linear
    -0.34
     organic
    -0.34
     intern
    -0.34
     industrial
    -0.33
     human
    -0.33
     social
    -0.32
     metall
    -0.32
    POSITIVE LOGITS
     choices
    0.34
     steps
    0.32
    (results
    0.32
     answer
    0.31
     selections
    0.31
     results
    0.30
    樣
    0.30
     options
    0.29
     answers
    0.29
     picks
    0.29
    Activations Density 35.089%

    No Known Activations