© 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. 1747
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas

    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
    麻麻
    -0.08
    pum
    -0.08
     Mans
    -0.07
    kien
    -0.07
    ãĥŁãĤ¢
    -0.07
    elm
    -0.07
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.07
    符
    -0.07
    beit
    -0.07
    (auto
    -0.07
    POSITIVE LOGITS
    essel
    0.07
    ixo
    0.07
    asin
    0.07
     Cola
    0.07
    ix
    0.07
    å¾IJ
    0.06
     casse
    0.06
    èĶ¡
    0.06
    éĩijä¸Ŀ
    0.06
    å°Ĩåĩºçİ°
    0.06
    Activations Density 0.315%

    No Known Activations