© 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. 34680
    Prev
    Next
    INDEX
    Explanations

    layout specifications

    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
    ModifiedDate
    -0.08
    -prepend
    -0.08
    æ¶ĪåĮĸåIJ¸æĶ¶
    -0.07
    stieg
    -0.07
    åıªç®¡
    -0.07
    orre
    -0.07
    (Mod
    -0.07
    ä¸ŀ
    -0.07
    одно
    -0.07
    modifier
    -0.07
    POSITIVE LOGITS
    æķ´ä¸ª
    0.13
     ìłĦì²´
    0.13
     entire
    0.12
    æķ´ä½ĵ
    0.12
    æĢ»
    0.12
     total
    0.12
    æĢ»çļĦ
    0.12
     keseluruhan
    0.12
    çļĦæķ´ä½ĵ
    0.11
    æĢ»éĿ¢ç§¯
    0.11
    Activations Density 0.227%

    No Known Activations