© 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. 22-TRANSCODER-HP
    7. 112804
    Prev
    Next
    INDEX
    Explanations

    Dates and years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¨Ģ
    -0.29
    æѤå¤Ħ
    -0.29
    pac
    -0.26
    åŀł
    -0.26
    èĩ³æѤ
    -0.26
    鹿
    -0.25
    å½ĵæĻļ
    -0.25
    irate
    -0.24
    ç½ij讯
    -0.24
    ir
    -0.24
    POSITIVE LOGITS
    ä¸ĢæĹı
    0.26
    å½Ģ
    0.25
     moderators
    0.25
    æľ¨æĿIJ
    0.24
    ä¼ijæģ¯
    0.24
    ãģ¾ãģĹãģ¦
    0.24
     resting
    0.24
    ért
    0.23
     nak
    0.23
    -half
    0.23
    Activations Density 0.017%

    No Known Activations