© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39557
    Prev
    Next
    INDEX
    Explanations

    restoring force

    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
    odox
    -0.08
    ä¹ĭè¡Į
    -0.08
    rette
    -0.08
    institu
    -0.07
    为èį£
    -0.07
    они
    -0.07
    è½°è½°
    -0.07
    æīĢæľīè¿ĻäºĽ
    -0.07
    etro
    -0.07
    -dropdown
    -0.07
    POSITIVE LOGITS
    cona
    0.07
    /reference
    0.07
    èĩªæĿ¥
    0.07
    νά
    0.07
    æ¾ľ
    0.06
    ráf
    0.06
    yun
    0.06
     Killer
    0.06
    æģ©æĸ¯
    0.06
    æ°ijé£İ
    0.06
    Activations Density 0.006%

    No Known Activations