© 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. 18081
    Prev
    Next
    INDEX
    Explanations

    main function entry point

    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
    人为
    -0.07
    éļıçĿĢ
    -0.06
    èį¡
    -0.06
    물
    -0.06
     (
    -0.06
    .Constraint
    -0.06
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.06
    obsolete
    -0.06
    éļıçĿĢæŶéĹ´çļĦ
    -0.06
    merce
    -0.06
    POSITIVE LOGITS
    ä¸īéĥ¨æĽ²
    0.08
    onia
    0.08
    ToStr
    0.08
    éŀłèº¬
    0.07
    ä¸įè¦ģéĶĻè¿ĩ
    0.07
    _CLEAN
    0.07
    èĴĤæĸ¯
    0.07
     préf
    0.07
    .cleanup
    0.07
    åį³æĹ¥èµ·
    0.07
    Activations Density 0.006%

    No Known Activations