© 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. 41386
    Prev
    Next
    INDEX
    Explanations

    all lists

    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
    å¾Īå¤ļåľ°æĸ¹
    -0.08
    æŁIJäºĽ
    -0.08
    æķ´ä½ĵçļĦ
    -0.08
    ç»ıå¸¸åľ¨
    -0.08
     itself
    -0.08
    è¾ĥå¤ļ
    -0.08
    å®Įåħ¨ä¸įåIJĮçļĦ
    -0.08
    veral
    -0.08
    大éĩı
    -0.08
     sometimes
    -0.08
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.23
     except
    0.18
     kecuali
    0.15
    æĪĸéĥ¨åĪĨ
    0.15
    except
    0.15
     sauf
    0.15
    Except
    0.15
     imaginable
    0.15
     Except
    0.13
    —including
    0.13
    Activations Density 0.398%

    No Known Activations