© 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. 65263
    Prev
    Next
    INDEX
    Explanations

    1st, 2nd, 3rd

    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
    éĶ¦æ¶Ľ
    -0.07
    两个æĸ¹éĿ¢
    -0.07
    ase
    -0.07
    /pm
    -0.07
    äºĮä¸ĸ
    -0.07
    вига
    -0.06
     thá»į
    -0.06
    akaran
    -0.06
     Snyder
    -0.06
    ogi
    -0.06
    POSITIVE LOGITS
    ë²Ī
    0.07
    è·¯éĢı
    0.07
    cpt
    0.07
    à¸łà¸´
    0.07
    ת
    0.06
    èĵ
    0.06
    大äºĨ
    0.06
    дзе
    0.06
    oling
    0.06
    inci
    0.06
    Activations Density 0.297%

    No Known Activations