© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28750
    Prev
    Next
    INDEX
    Explanations

    choice, size, model, database

    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
    顺
    -0.08
    åı¯äº«
    -0.07
    ä¾ĿéĿł
    -0.07
    _proto
    -0.06
    åħ¨éĿł
    -0.06
    áĢ±áĢ¬
    -0.06
     Contrib
    -0.06
    éĿł
    -0.06
    ç´§éĹŃ
    -0.06
    éļ
    -0.06
    POSITIVE LOGITS
    éĢĤåIJĪäºİ
    0.17
    éĢĤçĶ¨äºİ
    0.17
     suited
    0.16
    æĽ´éĢĤåIJĪ
    0.16
    éĢĤåIJĪ
    0.16
     appropriate
    0.15
    主è¦ģçĶ¨äºİ
    0.14
    éģ©åIJĪ
    0.14
    æľĢéĢĤåIJĪ
    0.14
    éĴĪ对ä¸įåIJĮ
    0.14
    Activations Density 0.210%

    No Known Activations