© 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. 32271
    Prev
    Next
    INDEX
    Explanations

    example or paradigm cases

    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
    ukaan
    -0.08
    ç¿°
    -0.07
    èIJ½èĦļ
    -0.07
    Å©
    -0.07
    èĮ¹
    -0.07
    æĺ¯æĪij们çļĦ
    -0.07
    ÑĤам
    -0.07
     ë§ī
    -0.06
    ordinate
    -0.06
    áīł
    -0.06
    POSITIVE LOGITS
    ä¾ĭåŃIJ
    0.13
    çļĦä¾ĭåŃIJ
    0.12
     example
    0.11
    åħ¸åŀĭçļĦ
    0.11
     examples
    0.11
    /example
    0.10
     exempl
    0.10
    example
    0.10
    examples
    0.10
     Äijiá»ĥn
    0.10
    Activations Density 0.182%

    No Known Activations