© 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. 24-TRANSCODER-HP
    7. 149488
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .this
    -0.25
    äter
    -0.25
    itat
    -0.24
    fully
    -0.24
     absent
    -0.24
    abee
    -0.24
    chein
    -0.23
    uhl
    -0.23
    itur
    -0.23
    SEE
    -0.23
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.37
    ä¸Ģç§į
    0.33
    æĺ¯ä¸Ģç§į
    0.28
    ç¬Ļ
    0.27
    ä¸Ģ个æĺ¯
    0.27
    ä¸įæĺ¯ä¸Ģ个
    0.26
    æīįç®Ĺ
    0.26
    éĴ¢æĿIJ
    0.26
    æĺ¯ä¸Ģ项
    0.26
    çļĦæĪIJæľ¬
    0.26
    Activations Density 0.902%

    No Known Activations