© 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. 40737
    Prev
    Next
    INDEX
    Explanations

    positive or false questions

    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
    uwe
    -0.08
    peat
    -0.07
    XHR
    -0.07
    æ·ij
    -0.07
    uolo
    -0.07
    oble
    -0.07
    riteln
    -0.07
    cimal
    -0.07
    reeNode
    -0.07
     пÑĢедпÑĢинима
    -0.07
    POSITIVE LOGITS
    éĩįçļĦ
    0.07
    ä¸įèĭŁ
    0.07
    Dear
    0.06
    éĿĴ
    0.06
    _API
    0.06
    éch
    0.06
    ikä
    0.06
    JV
    0.06
    覧
    0.06
    西æĸ¯
    0.06
    Activations Density 0.112%

    No Known Activations