© 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. 17991
    Prev
    Next
    INDEX
    Explanations

    in

    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
     today
    -0.49
    ä»Ĭ天
    -0.46
    ä»ĬæĹ¥
    -0.43
     Today
    -0.42
     tonight
    -0.42
    today
    -0.41
     yesterday
    -0.40
     tomorrow
    -0.40
    _today
    -0.39
    æĺ¨å¤©
    -0.38
    POSITIVE LOGITS
    é¢ijçİĩ
    0.30
     Popular
    0.28
    ãģ°
    0.27
     Bulg
    0.26
    Popular
    0.26
    oval
    0.26
    ator
    0.25
    ety
    0.25
    atar
    0.25
    è¯Ŀ
    0.24
    Activations Density 0.004%

    No Known Activations