© 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. 21137
    Prev
    Next
    INDEX
    Explanations

    releases community

    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
    æ±²
    -0.08
    åİ»åĪ°
    -0.07
    ZIA
    -0.07
    cka
    -0.07
    %E
    -0.07
     muestr
    -0.07
     ÑĪокола
    -0.07
    maan
    -0.07
     اÙĦÙĥÙĬÙħÙĬا
    -0.07
     ÑĩÑĤоб
    -0.07
    POSITIVE LOGITS
    0.16
    0.13
    éĵ®
    0.08
     ØĽ
    0.07
    ÃĤ
    0.07
     Saga
    0.07
    ë¥ĺ
    0.06
    åĬĽå£«
    0.06
    æĺ¾çĿĢ
    0.06
    幸
    0.06
    Activations Density 0.177%

    No Known Activations