© 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. 57935
    Prev
    Next
    INDEX
    Explanations

    chaos theory

    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
    åĨľæĿijåľ°åĮº
    -0.08
     maiden
    -0.08
     compil
    -0.07
    stown
    -0.07
     marsh
    -0.07
    /compiler
    -0.07
    æµĵæµĵ
    -0.07
    æıĴåľ¨
    -0.07
    editable
    -0.06
    ç»ijæīİ
    -0.06
    POSITIVE LOGITS
    æ¼±
    0.11
    è·¡
    0.09
    uschen
    0.08
    วà¸Ļ
    0.08
    迹
    0.08
    UCT
    0.08
    ëĵ¬
    0.08
    çķ´
    0.08
    dict
    0.08
    èijµ
    0.07
    Activations Density 0.018%

    No Known Activations