© 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. 16539
    Prev
    Next
    INDEX
    Explanations

    function composition

    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
    och
    -0.08
    -plane
    -0.07
    ä¹īåĬ¡çļĦ
    -0.07
    .TryParse
    -0.07
    æ³¢ç½Ĺ
    -0.06
    uck
    -0.06
    *)_
    -0.06
     dán
    -0.06
    apa
    -0.06
    é½IJå¿ĥ
    -0.06
    POSITIVE LOGITS
    éĻħ
    0.07
    ickle
    0.07
    大æĺİ
    0.07
    ä¸ĢåľĪ
    0.07
    _pk
    0.07
    нено
    0.07
    ä½łä¸įçŁ¥éģĵ
    0.07
    emor
    0.07
    æŶéĹ´æ®µ
    0.07
    æīĢå±ŀåĪĨç±»
    0.06
    Activations Density 0.016%

    No Known Activations