© 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. 7099
    Prev
    Next
    INDEX
    Explanations

    years or ml

    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
    Negative Logits
    ssen
    -0.08
    à¥Ĥस
    -0.08
    deo
    -0.08
    èĸĩèĸĩ
    -0.08
    оÑĤов
    -0.07
    æĶ¹åıĺèĩªå·±
    -0.07
    æ±IJ
    -0.07
    stown
    -0.07
    ondon
    -0.07
    à¹Ģà¸Ļà¹ĩà¸ķ
    -0.07
    POSITIVE LOGITS
    yman
    0.08
    çļĦ
    0.08
    empl
    0.07
    cope
    0.07
    çĶ¨åĵģæľīéĻIJåħ¬åı¸
    0.07
    phere
    0.07
    quine
    0.06
    Ñĩами
    0.06
    .defaults
    0.06
    iday
    0.06
    Activations Density 0.001%

    No Known Activations