© 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. 51646
    Prev
    Next
    INDEX
    Explanations

    universality and scaling exponents

    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
    é¦Ī
    -0.07
    娴
    -0.07
    vecs
    -0.07
    earer
    -0.07
     vag
    -0.07
    abend
    -0.07
     aliqu
    -0.06
    vag
    -0.06
     sim
    -0.06
    å·¥ç¨ĭæľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    æĢģ
    0.08
    å¼ĹéĩĮ
    0.07
    ificent
    0.07
    é¢Ħè¨Ģ
    0.07
     Ñģке
    0.07
     exponent
    0.07
    è·¨çķĮ
    0.07
    univers
    0.07
    åĩĿèģļ
    0.07
    scaling
    0.07
    Activations Density 0.044%

    No Known Activations