© 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. 58350
    Prev
    Next
    INDEX
    Explanations

    url paths and dates

    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
    omon
    -0.08
    绾ç»İ
    -0.06
    dek
    -0.06
    aka
    -0.06
    èĢĮåIJİ
    -0.05
    uguay
    -0.05
    ignano
    -0.05
    itar
    -0.05
    aeda
    -0.05
    ä¸Ģå¼łå¼ł
    -0.05
    POSITIVE LOGITS
    æĶ¶èĹıæľ¬ç«Ļ
    0.10
    .Configure
    0.09
    订éĺħä¸ĵæłı
    0.09
    çīĪä¸ĭè½½
    0.08
    ä¸ŃéĿĴ
    0.08
    ðŁĺĢ
    0.08
    é¡¹çĽ®è¿Ľè¡Į
    0.08
    ä¹ĭä¸į
    0.08
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.07
    amil
    0.07
    Activations Density 0.043%

    No Known Activations