© 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. 13403
    Prev
    Next
    INDEX
    Explanations

    file types or programming constructs

    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
    æİĴ
    -0.08
    çĽĸä¸Ĭ
    -0.08
    ç¹ģ
    -0.07
    acara
    -0.07
    aktur
    -0.07
     Jabar
    -0.07
    ;;;;
    -0.07
    acket
    -0.07
    awang
    -0.07
    agy
    -0.07
    POSITIVE LOGITS
    æŁ¥çľĭåħ¨éĥ¨
    0.07
    Ñħина
    0.07
    uming
    0.07
    kas
    0.07
    并ä¸įé«ĺ
    0.07
     unin
    0.07
     вÑĭÑģÑĭ
    0.06
    ä¸įèĩª
    0.06
    ä¸Ĭå¸ĤåIJİ
    0.06
    ripper
    0.06
    Activations Density 0.119%

    No Known Activations