© 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. 50801
    Prev
    Next
    INDEX
    Explanations

    null, NAN, NotNull

    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
    ansch
    -0.10
    ä¸į误
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    çŁ¥éģĵæĪij
    -0.09
    bacher
    -0.09
    less
    -0.09
    LESS
    -0.09
    ä¸įå¿ĺåĪĿå¿ĥ
    -0.09
    allery
    -0.09
     недоÑģÑĤаÑĤоÑĩно
    -0.08
    POSITIVE LOGITS
    oriously
    0.12
    æĪĸå°ij
    0.11
    withstanding
    0.11
     yet
    0.09
     obstante
    0.09
    寻常
    0.09
    ional
    0.09
    çĦ¶æĺ¯
    0.08
     necessarily
    0.08
    约èĢĮåIJĮ
    0.08
    Activations Density 0.013%

    No Known Activations