© 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. 38558
    Prev
    Next
    INDEX
    Explanations

    Western Canada places

    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
    *A
    -0.29
    &o
    -0.27
    ä¸Ģåī¯
    -0.26
     O
    -0.25
    oco
    -0.24
     A
    -0.24
     Luxury
    -0.24
    umatic
    -0.24
    oped
    -0.23
    notin
    -0.23
    POSITIVE LOGITS
    ï¼İ
    0.32
     ///
    0.26
     retire
    0.26
    ä¸Ńå¤ĸ
    0.25
     Kimber
    0.25
     Burl
    0.25
     vet
    0.25
    æĿijåŃIJ
    0.25
    ês
    0.24
     fatt
    0.24
    Activations Density 0.003%

    No Known Activations