© 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. 24170
    Prev
    Next
    INDEX
    Explanations

    çļħ and related tokens

    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
    íĻĶìĿĺ
    -0.13
    çļĦæŶåĢĻä¼ļ
    -0.12
     ë¶Ħìķ¼ìĿĺ
    -0.11
    ëŁīìĿĺ
    -0.11
    ä¸įåIJĮçļĦæĺ¯
    -0.11
    ìĥģìĿĺ
    -0.11
    çļĦæĸ¹å¼ıè¿Ľè¡Į
    -0.11
    çļĦåŁºç¡Ģä¸Ĭ
    -0.11
    ìĿ´ìĿĺ
    -0.11
    çļĦæĸ¹å¼ı
    -0.11
    POSITIVE LOGITS
    èĢħ们
    0.08
    ,
    0.07
    (de
    0.07
    åĩĨå¤ĩå·¥ä½ľ
    0.06
    æĢ§å·¥ä½ľ
    0.06
    å±ĭãģķãĤĵ
    0.06
    '
    0.06
    ç»ĦæĪIJéĥ¨åĪĨ
    0.06
    ä»ĬçĶŁ
    0.06
    oretical
    0.06
    Activations Density 0.039%

    No Known Activations