© 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. 18243
    Prev
    Next
    INDEX
    Explanations

    coordinates or punctuation

    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
    èĸª
    -0.07
    è°ĥ
    -0.07
    åĢ¼
    -0.07
    ulte
    -0.07
    avat
    -0.06
    ç§ī
    -0.06
    ëĭ¨
    -0.06
    iest
    -0.06
    æĮij
    -0.06
    gil
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.10
     coordinates
    0.09
    ä¸īçĤ¹
    0.09
    çĤ¹åĴĮ
    0.08
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.08
    çĤ¹ãģ¯
    0.08
    çĤ¹è¿Ľè¡Į
    0.08
    çĤ¹æĺ¯
    0.08
     QPoint
    0.08
    è·ĿéĽ¢
    0.08
    Activations Density 0.004%

    No Known Activations