© 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. 46211
    Prev
    Next
    INDEX
    Explanations

    mathematical results and logic

    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
    isca
    -0.09
    oldown
    -0.08
    leftright
    -0.08
    APPER
    -0.08
     rece
    -0.08
    cind
    -0.08
    ç¡
    -0.07
     prév
    -0.07
    .dest
    -0.07
    }@
    -0.07
    POSITIVE LOGITS
     regardless
    0.06
     puzz
    0.06
    类似çļĦ
    0.06
    azor
    0.06
    æľīåħ³çļĦ
    0.06
    æľīæŶä¼ļ
    0.06
    åħ»æĪIJèī¯å¥½çļĦ
    0.06
    uhr
    0.06
     peculiar
    0.06
    å¾Īæ¼Ĥ亮
    0.05
    Activations Density 0.011%

    No Known Activations