© 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. 16658
    Prev
    Next
    INDEX
    Explanations

    nonprofit organizations

    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
    _ORIGIN
    -0.07
    æ§Ľ
    -0.07
    LEV
    -0.07
    ÃīT
    -0.07
    øy
    -0.07
     convinc
    -0.07
    baugh
    -0.07
    æł¡é¢Ĩ导
    -0.07
    onas
    -0.07
    ÃīR
    -0.07
    POSITIVE LOGITS
    人äºĭ
    0.08
    å·¥ä½ľèĢħ
    0.08
    ivate
    0.07
    æħµ
    0.07
    çĽ
    0.07
    é¹ĥ
    0.07
    çIJ´
    0.07
    ä½ĵåĪ¶æĶ¹éĿ©
    0.07
    ufs
    0.06
    ç±»åŀĭ为
    0.06
    Activations Density 0.001%

    No Known Activations