© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    you can

    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
    æľªå¿ħ
    -0.09
    ä¸Ģå®ļç¨ĭ度
    -0.08
    èĭ¥éĿŀ
    -0.08
    å¹²åĺĽ
    -0.07
    å¦Ĥæŀľä¸įæĺ¯
    -0.07
    å½ĵæŶ
    -0.07
    èĭ¥åľ¨
    -0.07
    æŁIJç§į
    -0.07
    akin
    -0.07
    æŁIJäºĽ
    -0.07
    POSITIVE LOGITS
    粧
    0.08
    éĺ³åİ¿
    0.07
    amage
    0.07
    óch
    0.07
    注åĨĮèµĦæľ¬ä¸º
    0.07
    æĪij们éĥ½ä¼ļ
    0.07
    âĤ¬.
    0.07
     arro
    0.07
     conséquent
    0.07
    éļıå¿ĥ
    0.07
    Activations Density 0.011%

    No Known Activations