© 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. 32006
    Prev
    Next
    INDEX
    Explanations

    I need, don't, pursuit

    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
     consequently
    -0.10
     accordingly
    -0.09
     ÑģооÑĤвеÑĤÑģÑĤвенно
    -0.09
     meanwhile
    -0.08
     ÑģледоваÑĤелÑĮно
    -0.08
     наконеÑĨ
    -0.08
    åį´æ²¡
    -0.08
    åıĪå¦Ĥ
    -0.08
    ä½łåij¢
    -0.07
     portanto
    -0.07
    POSITIVE LOGITS
    æĮº
    0.09
    并ä¸įéľĢè¦ģ
    0.09
     quite
    0.08
    tors
    0.07
    并ä¸į
    0.07
    å¹¶æľª
    0.07
    并没æľī
    0.06
    ä¸į太
    0.06
    ummer
    0.06
    æĽ´å¥½
    0.06
    Activations Density 0.093%

    No Known Activations