© 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. 57059
    Prev
    Next
    INDEX
    Explanations

    probability and optimization models

    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
    дÑĢе
    -0.07
    åĸĿéħĴ
    -0.07
    andr
    -0.07
     yatır
    -0.07
     horizontal
    -0.07
    彫
    -0.06
    iato
    -0.06
    åĬªåĬĽå®ŀçİ°
    -0.06
    iette
    -0.06
    iot
    -0.06
    POSITIVE LOGITS
    å¦Ĥ鼨
    0.10
     likelihood
    0.08
    éĺ³æĺ¥
    0.08
    likelihood
    0.08
    ä¼¼
    0.08
     Lik
    0.07
     Rice
    0.07
    prob
    0.07
    æĬij
    0.07
    _PIXEL
    0.07
    Activations Density 0.009%

    No Known Activations