© 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. 14143
    Prev
    Next
    INDEX
    Explanations

    Predicting risks and outcomes

    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
    opter
    -0.08
    ure
    -0.07
    adoo
    -0.06
    大éĩı
    -0.06
    çĿĢ
    -0.06
    addon
    -0.06
    çĿĢä¸Ģ
    -0.06
     pertaining
    -0.06
    ëŀĺ
    -0.06
     whichever
    -0.06
    POSITIVE LOGITS
    ä¸İç»´æĬ¤
    0.08
     пÑĢавда
    0.08
     ÑģквозÑĮ
    0.08
    åĴĮä¼ĺåĮĸ
    0.08
    ÃŃv
    0.08
    çĮľä½łåĸľæ¬¢
    0.07
    åĴĮç»´æĬ¤
    0.07
    åĴĮçIJĨ解
    0.07
    ithe
    0.07
    åĴĮæıIJé«ĺ
    0.07
    Activations Density 0.330%

    No Known Activations