© 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. 15710
    Prev
    Next
    INDEX
    Explanations

    code headers and operators

    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
     Nunes
    -0.08
    ensp
    -0.07
    ög
    -0.07
    FLAGS
    -0.07
    LastError
    -0.06
    emann
    -0.06
    ä¸įèĥľ
    -0.06
    _WH
    -0.06
    uy
    -0.06
    éĩijç§ĭ
    -0.06
    POSITIVE LOGITS
    oss
    0.07
     Szer
    0.07
    _utilities
    0.07
     infine
    0.07
    alp
    0.07
    ç«¥åŃIJ
    0.07
    inals
    0.06
    -expression
    0.06
     puss
    0.06
    æıīäºĨ
    0.06
    Activations Density 0.002%

    No Known Activations