© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42329
    Prev
    Next
    INDEX
    Explanations

    contrast or exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įåıij
    -0.09
    ä¸įå¤ĸ
    -0.09
    asseur
    -0.09
    ream
    -0.09
    iglia
    -0.08
    ä¸įç®¡ä½ł
    -0.08
    转载æĪĸå¼ķçĶ¨
    -0.08
    leos
    -0.08
    chio
    -0.08
    .Pe
    -0.08
    POSITIVE LOGITS
    æİĮæı¡
    0.07
    æ¸Ī
    0.06
     valid
    0.06
    w
    0.06
    ç¡®
    0.06
    åį´æľī
    0.06
    æĪ·æĪ·
    0.06
    åħ¨åĬĽ
    0.06
    éļ
    0.06
    valid
    0.05
    Activations Density 0.064%

    No Known Activations