© 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. 4578
    Prev
    Next
    INDEX
    Explanations

    functions on p

    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
    planes
    -0.07
    OptionsMenu
    -0.07
     juntas
    -0.07
    /download
    -0.06
    uron
    -0.06
    ä¼ģ
    -0.06
    å¢ĥåĨħçļĦ
    -0.06
    ائÙĨ
    -0.06
    inition
    -0.06
    ä¹ĭè§Ħå®ļ
    -0.06
    POSITIVE LOGITS
    åŀĭåĴĮ
    0.07
    TypeInfo
    0.07
    ecter
    0.07
    æĺ¯å®Įåħ¨
    0.07
    æľĪåĴĮ
    0.07
    allery
    0.06
    ál
    0.06
    eguire
    0.06
    ÙĪØ´
    0.06
    ctions
    0.06
    Activations Density 0.009%

    No Known Activations