© 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. 9581
    Prev
    Next
    INDEX
    Explanations

    website, code, and configuration keys

    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
    åŃIJæĽ°
    -0.08
    ادر
    -0.07
     extr
    -0.07
    áŀ·áŀı
    -0.06
    andt
    -0.06
     Bre
    -0.06
    æ¯ıåŃ¦æľŁ
    -0.06
    omap
    -0.06
    éĻIJæľŁ
    -0.06
    ież
    -0.06
    POSITIVE LOGITS
    ĤŃ
    0.07
    驹
    0.07
    è²
    0.07
    vil
    0.07
    åĨĢ
    0.07
    å°ıåı¶
    0.07
    è¦ģæıIJé«ĺ
    0.07
    ä¸īéĢļ
    0.07
    èĬĿ
    0.06
    à¤Łà¤¨à¤¾
    0.06
    Activations Density 0.152%

    No Known Activations