© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63796
    Prev
    Next
    INDEX
    Explanations

    still nothing

    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
     blatantly
    -0.08
    绾ç»İä¸įç»Ŀ
    -0.08
    mium
    -0.08
    stry
    -0.08
    uplic
    -0.07
     عزÙĬز
    -0.07
    æīĢåĮħåIJ«
    -0.07
    iffer
    -0.07
    æĽ´åĬłæĸ¹ä¾¿
    -0.07
    æīĢæıIJä¾ĽçļĦ
    -0.07
    POSITIVE LOGITS
     a
    0.08
     yours
    0.08
     ê·¸ëłĩ
    0.07
    è¿Ľè¡Įä¸Ń
    0.07
    ly
    0.07
    æľī人
    0.07
    มีà¸ģาร
    0.07
    æĻļäºĨ
    0.06
     done
    0.06
    åĬłæĭ¿å¤§
    0.06
    Activations Density 0.145%

    No Known Activations