© 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. 45993
    Prev
    Next
    INDEX
    Explanations

    musicians and politicians

    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
    éĢļ常æĥħåĨµä¸ĭ
    -0.07
    ä¸İ该
    -0.07
    ä¸ŃçļĦä¸Ģç§į
    -0.06
    éĢļ常
    -0.06
     Normally
    -0.06
    çļĦä¸Ģç§į
    -0.06
    getColumn
    -0.06
    ickness
    -0.06
    adden
    -0.06
    Normally
    -0.06
    POSITIVE LOGITS
    ä¹ĭäºİ
    0.09
    çŃīä¸Ģæī¹
    0.08
    为代表çļĦ
    0.08
    为代表
    0.08
    éĤ£æł·
    0.08
     például
    0.08
    éĤ£æ¨£
    0.08
    edig
    0.07
    ä¹Łå¥½
    0.07
     versus
    0.07
    Activations Density 0.033%

    No Known Activations