© 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. 32-TRANSCODER-HP
    7. 44239
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ãĢĤãĢĮ
    -0.40
    ãĢģãĢĮ
    -0.36
    ãĢĮ
    -0.35
     ãĢĮ
    -0.34
     «
    -0.34
     Queries
    -0.30
     '[
    -0.29
     Arrays
    -0.29
     '**
    -0.29
    .toArray
    -0.28
    POSITIVE LOGITS
     piece
    0.44
    piece
    0.37
    pieces
    0.35
    -piece
    0.33
     pieces
    0.33
    è¿Ļä¸ªåľ°æĸ¹
    0.29
    _piece
    0.28
    Piece
    0.28
    Pieces
    0.27
     place
    0.27
    Activations Density 0.001%

    No Known Activations