© 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. 111090
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Negative Logits
    Č↵
    -0.29
    æĺ¯åľ¨
    -0.28
     uy
    -0.25
    á»ĩp
    -0.25
    Č
    -0.25
    æĺ¯ä¸ŃåĽ½
    -0.24
    Ĺ
    -0.24
     is
    -0.24
    黼
    -0.24
     bölümü
    -0.24
    POSITIVE LOGITS
    lâ
    0.29
    áln
    0.27
    зам
    0.25
    éĨª
    0.24
     Wand
    0.24
    æijĩäºĨ
    0.24
    [--
    0.24
     RANDOM
    0.23
    constitution
    0.23
    ighthouse
    0.23
    Activations Density 0.012%

    No Known Activations