© 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. 129243
    Prev
    Next
    INDEX
    Explanations

    technology, support, instructions

    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
     Abyss
    -0.25
    设计æĸ¹æ¡Ī
    -0.24
     Ashe
    -0.24
     metic
    -0.24
     Spicer
    -0.24
     genom
    -0.24
    rades
    -0.23
    reich
    -0.23
    ycin
    -0.23
    opr
    -0.23
    POSITIVE LOGITS
    Char
    0.28
    li
    0.28
    lib
    0.27
    ä¸įç¦ģ
    0.26
    PI
    0.25
    pi
    0.25
    char
    0.25
    .bus
    0.24
    们
    0.24
    lo
    0.23
    Activations Density 0.016%

    No Known Activations