© 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. 61553
    Prev
    Next
    INDEX
    Explanations

    beauty and the sublime

    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
    illet
    -0.07
    åĬ¡å®ŀ
    -0.07
     Artes
    -0.07
     stabilit
    -0.07
    åĭ¤
    -0.06
    argon
    -0.06
    æ¯ıåIJį
    -0.06
    ulen
    -0.06
    .every
    -0.06
     ambit
    -0.06
    POSITIVE LOGITS
    让人æĦŁåĪ°
    0.09
    çļĦäºĭçī©
    0.09
    çī©ä½ĵ
    0.09
    äºĭçī©
    0.08
    çļĦ人类
    0.08
    对象çļĦ
    0.08
    çĻ»é«ĺ
    0.08
     sublime
    0.08
     objects
    0.08
    æĦŁåĪ°äºĨ
    0.08
    Activations Density 0.015%

    No Known Activations