© 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. 27424
    Prev
    Next
    INDEX
    Explanations

    questions and their related issues

    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
    gup
    -0.09
     daarvan
    -0.09
    estro
    -0.09
    æŁ¥çľĭæĽ´å¤ļä¿¡æģ¯
    -0.08
    éĪį
    -0.08
    æ°¸è¿ľæĺ¯
    -0.08
    京åħ¬ç½ijå®īå¤ĩ
    -0.08
    sunami
    -0.08
    lach
    -0.08
    สà¸Ļิà¸Ĺ
    -0.08
    POSITIVE LOGITS
    ä¸ĵä¸ļæĢ§
    0.08
    å¤ļæĸ¹éĿ¢
    0.07
    ä¸įç®Ģåįķ
    0.07
    _
    0.07
    ator
    0.06
    çľĭä¼¼
    0.06
    on
    0.06
    pte
    0.06
    ç»ĵåIJĪäºĨ
    0.06
    èĢĥéªĮ
    0.06
    Activations Density 0.002%

    No Known Activations