© 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. 40121
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    akwa
    -0.08
    oooooooo
    -0.07
    oker
    -0.07
    &T
    -0.07
    ستÛĮ
    -0.07
    å°ıæľī
    -0.07
    иден
    -0.07
     demais
    -0.07
    ¡´
    -0.07
    &R
    -0.07
    POSITIVE LOGITS
    大åħ³
    0.07
    éĿŀ
    0.07
    âĢ
    0.06
    æı£
    0.06
    .gz
    0.06
    æķ£
    0.06
    éŨå¸Ĥ
    0.06
    ëĭ¤ìļ´
    0.06
    æĭ·
    0.06
    çıįå®Ŀ
    0.06
    Activations Density 0.181%

    No Known Activations