© 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. 18722
    Prev
    Next
    INDEX
    Explanations

    home

    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
    ä¹ħ
    -0.07
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.07
     frem
    -0.07
    æ£ł
    -0.07
    _catalog
    -0.06
    roke
    -0.06
    æķ°çĽ®
    -0.06
    æľĹ
    -0.06
    åĪ¥
    -0.06
    Dup
    -0.06
    POSITIVE LOGITS
     locating
    0.12
    åľ¨åĵªéĩĮ
    0.11
    æ´»åĬ¨åľ°çĤ¹
    0.11
     ÑĢаÑģполагаеÑĤÑģÑı
    0.11
    ãģ¯ãģ©ãģĵ
    0.11
     locate
    0.11
    locate
    0.11
     ìĸ´ëĶĶ
    0.10
    çļĦä½įç½®
    0.10
     location
    0.10
    Activations Density 0.347%

    No Known Activations