© 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. 29539
    Prev
    Next
    INDEX
    Explanations

    html entities and tags

    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
    2
    -0.08
    3
    -0.07
    åıĸå¾ĹçļĦæĪIJ绩
    -0.07
    ality
    -0.07
    4
    -0.07
    ness
    -0.07
    ÑīÑĸ
    -0.07
    å¾Ĺä¸į
    -0.07
    oo
    -0.06
    ä¸ŃçļĦæķ°æį®
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.12
    çļĦ
    0.11
    ï¸İ
    0.10
    nya
    0.09
    ÛĮ
    0.09
    à¹Į
    0.08
    ุม
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    åľ¨
    0.08
    иÑĢованиÑı
    0.08
    Activations Density 0.037%

    No Known Activations