© 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. 55687
    Prev
    Next
    INDEX
    Explanations

    allows string array

    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
     maybe
    -0.07
    ä¾ĭå¦Ĥ
    -0.07
     some
    -0.07
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    -0.07
    ä¸ĢäºĽ
    -0.07
    æŁIJäºĽ
    -0.07
     perhaps
    -0.07
    å¦Ĥåħ¶
    -0.07
    çļĦä¸ĢäºĽ
    -0.07
    æ¯Ķå¦Ĥ
    -0.07
    POSITIVE LOGITS
    ãģĤãģı
    0.10
    ç¡®ä¿ĿäºĨ
    0.09
    æĹ¢æĺ¯
    0.08
    æĹ¢èĥ½
    0.08
     ìĿ´ì²ĺëŁ¼
    0.08
    æĹ¢åı¯
    0.08
    åĭĴæĸ¯
    0.08
    resse
    0.08
    客çļĦ
    0.08
    ä¸įåĽł
    0.08
    Activations Density 0.010%

    No Known Activations