© 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. 129231
    Prev
    Next
    INDEX
    Explanations

    surnames

    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
    æĽ´å¤ļ
    -0.33
    ä¸İåIJ¦
    -0.30
     why
    -0.29
    æĽ´å¤ļä¿¡æģ¯
    -0.28
    å¦Ĥä½ķ
    -0.28
     hvordan
    -0.26
    how
    -0.26
    @",
    -0.25
    为ä½ķ
    -0.25
    ä¸į足
    -0.25
    POSITIVE LOGITS
    itable
    0.28
    èļĵ
    0.28
    kit
    0.27
    //{{
    0.27
    .FONT
    0.26
    lands
    0.26
     invit
    0.25
    饱åĴĮ
    0.25
    logs
    0.24
    sequelize
    0.24
    Activations Density 0.205%

    No Known Activations