© 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. 31-TRANSCODER-HP
    7. 17797
    Prev
    Next
    INDEX
    Explanations

    Light/Brightness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ilian
    -0.30
    assador
    -0.27
     Marxist
    -0.26
    æ§İ
    -0.25
     Radical
    -0.25
    missão
    -0.24
     ceremonial
    -0.24
    ç»ĵ
    -0.24
    adel
    -0.24
    SAN
    -0.24
    POSITIVE LOGITS
    æĸĽ
    0.31
    _OFFSET
    0.28
     golden
    0.28
    è§Ĩéĩİ
    0.28
    æĸĹ
    0.27
     safe
    0.27
     hot
    0.27
     appearance
    0.25
     dark
    0.25
     errone
    0.25
    Activations Density 0.879%

    No Known Activations