© 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. 65068
    Prev
    Next
    INDEX
    Explanations

    one or

    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
    æī¾æĿ¥
    -0.07
    æĸ°å¢ŀ
    -0.06
    .share
    -0.06
    imest
    -0.06
    _constraints
    -0.06
    aidu
    -0.06
     Counsel
    -0.06
     Boll
    -0.06
    çķª
    -0.06
    åIJĪ约
    -0.06
    POSITIVE LOGITS
    å·§å¦Ļ
    0.08
    (method
    0.08
    hluk
    0.08
    ä¸Ī
    0.08
    ç»Ŀå¢ĥ
    0.07
    æĥ³è®©
    0.07
    è¿Ļ个æĸ¹æ³ķ
    0.07
    åĭĩæķ¢åľ°
    0.07
    _backend
    0.07
    agne
    0.07
    Activations Density 0.001%

    No Known Activations