© 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. 48241
    Prev
    Next
    INDEX
    Explanations

    all or both

    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
    ç¥ī
    -0.07
    æĺ¯åIJ¦åŃĺåľ¨
    -0.07
     thù
    -0.06
    第ä¸īæī¹
    -0.06
    forms
    -0.06
    кан
    -0.06
    form
    -0.06
     rép
    -0.06
     anything
    -0.06
    ç»ıæľ¬éĻ¢
    -0.06
    POSITIVE LOGITS
    /all
    0.09
    æĪĸéĥ¨åĪĨ
    0.09
    })",
    0.08
    ÙıÙĪ
    0.07
    ÑĢеменно
    0.07
    éĥ½ä¸įçĶ¨
    0.07
    undes
    0.07
    uding
    0.07
    dbh
    0.07
    simd
    0.07
    Activations Density 0.017%

    No Known Activations