© 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. 12431
    Prev
    Next
    INDEX
    Explanations

    numbers or ranges

    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
    chter
    -0.07
    第ä¸Ģ件äºĭ
    -0.07
     part
    -0.07
    ä¹Łæĺ¯æĪij
    -0.07
    alc
    -0.07
    ãģĽãģ£
    -0.07
    éĿŀçī©è´¨
    -0.07
    æīĢ幸
    -0.06
    aller
    -0.06
    ('('
    -0.06
    POSITIVE LOGITS
     Ñĥгодно
    0.07
    anges
    0.07
    abol
    0.07
    æĽĻ
    0.07
    IgnoreCase
    0.07
    åį³æĹ¥èµ·èĩ³
    0.07
    ÑĢики
    0.07
    ometers
    0.06
    imits
    0.06
    imps
    0.06
    Activations Density 0.068%

    No Known Activations