© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7240
    Prev
    Next
    INDEX
    Explanations

    variable assignment or code block

    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
    iedz
    -0.08
    ächt
    -0.08
    áĥĶáĥĹ
    -0.08
     opie
    -0.07
    æľīæĪij
    -0.07
    縮
    -0.07
    ä¿±è¿Ľ
    -0.07
    abouts
    -0.07
    oload
    -0.07
    ary
    -0.07
    POSITIVE LOGITS
    èĮ¬
    0.07
    CEL
    0.06
    æģ©
    0.06
    enu
    0.06
    å·¡åĽŀ
    0.06
    elm
    0.06
    çĿĽ
    0.06
    oker
    0.06
    itch
    0.06
    enko
    0.06
    Activations Density 0.001%

    No Known Activations