© 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. 29617
    Prev
    Next
    INDEX
    Explanations

    cartilage, space, coracoid, arm, underside

    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
    ä¹Łç½¢
    -0.08
     Imp
    -0.08
    Imp
    -0.07
    zett
    -0.07
    åıªæľīéĢļè¿ĩ
    -0.07
    aisu
    -0.07
    åľ¨éĩĮéĿ¢
    -0.07
    inar
    -0.07
    æŶéĹ´å®īæİĴ
    -0.07
    æĬĬèĩªå·±
    -0.07
    POSITIVE LOGITS
    ấy
    0.08
     appena
    0.08
    æŃ£ä¸Ń
    0.07
    交æ±ĩå¤Ħ
    0.07
    梨
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    쯤
    0.07
    å¤§çº¦åľ¨
    0.07
     onStop
    0.07
    æĿ¥åºĹ
    0.07
    Activations Density 0.018%

    No Known Activations