© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11871
    Prev
    Next
    INDEX
    Explanations

    Seinfeld, Outkast, The Saint

    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
     Ton
    -0.06
    ä¸įåıĺ
    -0.06
     lẫn
    -0.05
    æľŁåĴĮ
    -0.05
    (crate
    -0.05
    à¹Ģà¸Ńà¸ĩ
    -0.05
    é»ijåIJįåįķ
    -0.05
     perfect
    -0.05
    ä¸Ĭå¸ĤçļĦ
    -0.05
    Perfect
    -0.05
    POSITIVE LOGITS
    åįģåĪĨéĩįè¦ģçļĦ
    0.09
    unner
    0.08
    .unique
    0.08
    гÑĢада
    0.08
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    wegs
    0.07
    ä¼łåªĴ
    0.07
    ãĥ³ãĤ°
    0.07
     váºŃy
    0.07
    truncate
    0.07
    Activations Density 0.091%

    No Known Activations