© 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. 11599
    Prev
    Next
    INDEX
    Explanations

    sorting and comparing numbers

    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
    annot
    -0.07
    åĭĩæķ¢åľ°
    -0.07
     +-
    -0.06
    ä¸įå¾Ĺ使çĶ¨
    -0.06
    sdale
    -0.06
    yu
    -0.06
     +%
    -0.06
    为å¥ijæľº
    -0.06
    elson
    -0.06
    anza
    -0.06
    POSITIVE LOGITS
    åŃļ
    0.09
     Depending
    0.09
    Depending
    0.09
    åıĸåĨ³äºİ
    0.08
     depending
    0.08
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    0.08
     Depends
    0.08
    creds
    0.07
    éĻ¤éĿŀ
    0.07
    éĢļ常æĥħåĨµä¸ĭ
    0.07
    Activations Density 0.002%

    No Known Activations