© 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. 61500
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain words

    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
    åıĮ羸
    -0.07
    彬
    -0.07
    èIJ½èIJ½
    -0.07
    人æĦı
    -0.06
     Ones
    -0.06
    滨æ¹ĸ
    -0.06
    æīĢå¼ķèµ·çļĦ
    -0.06
    æIJı
    -0.06
    å¯Ħ
    -0.06
    uy
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.10
    rames
    0.09
    -wide
    0.08
    alls
    0.08
    å¾Īå¤ļäºĭæĥħ
    0.08
    举åĮĹéĥ¨
    0.07
     Kurd
    0.07
    rane
    0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    è¿Ļ个éģĵçIJĨ
    0.07
    Activations Density 0.017%

    No Known Activations