© 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. 111088
    Prev
    Next
    INDEX
    Explanations

    Units of measurement

    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
    bir
    -0.26
    ;charset
    -0.26
     Anaheim
    -0.25
    å¹´ä¹ĭä¹ħ
    -0.25
    peria
    -0.24
     Gujar
    -0.24
    avigator
    -0.23
    åľ¨åŃ¦æł¡
    -0.23
    icago
    -0.23
    awaii
    -0.23
    POSITIVE LOGITS
    åĨ²æ´Ĺ
    0.29
    олÑĮ
    0.29
    /
    0.27
     Id
    0.25
    举
    0.24
    /R
    0.24
     Initial
    0.24
    ç¨ĭå¼ı
    0.23
    à¹Īาย
    0.23
     PROGRAM
    0.23
    Activations Density 0.013%

    No Known Activations