© 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. 43983
    Prev
    Next
    INDEX
    Explanations

    groups of individuals or entities

    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
    çļĦå·¥ä½ľä¸Ń
    -0.06
    ovan
    -0.06
    ĵĴ
    -0.06
    ussen
    -0.06
    çĨŁèĥ½
    -0.06
    è¿Ľä¸ĢæŃ¥æī©å¤§
    -0.06
    Ñīенко
    -0.06
     заклÑİÑĩаеÑĤÑģÑı
    -0.06
    ØŃاء
    -0.06
    å·¥ä½ľä¸Ĭ
    -0.06
    POSITIVE LOGITS
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.09
     بÛĮشترÛĮ
    0.09
    ä¹ĭæīĢ以
    0.09
     undergo
    0.08
    ÙĮ
    0.08
     often
    0.08
     زÛĮادÛĮ
    0.08
     rarely
    0.07
    ç»ı常被
    0.07
     exhibiting
    0.07
    Activations Density 0.377%

    No Known Activations