© 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. 17303
    Prev
    Next
    INDEX
    Explanations

    variable names and code syntax

    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
    èĤĨ
    -0.08
    å¿ħä¸įåı¯
    -0.07
    æį·
    -0.07
    度çļĦ
    -0.06
    Ùħر
    -0.06
    ç«¯æľ¨
    -0.06
    ØŃات
    -0.06
    _possible
    -0.06
    /ml
    -0.06
    éĵ¶å±±
    -0.06
    POSITIVE LOGITS
    äk
    0.08
    æ¥ł
    0.07
    ì²ľ
    0.07
    ạch
    0.07
    IfExists
    0.07
    koch
    0.07
    æĭľ
    0.07
    пиÑģка
    0.07
     Commonwealth
    0.07
    çĦ¶å¤§
    0.07
    Activations Density 0.023%

    No Known Activations