© 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. 32338
    Prev
    Next
    INDEX
    Explanations

    article cited or published

    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
    .amazonaws
    -0.09
    etro
    -0.08
    çĦ¶å¤§
    -0.08
    ÑģпоÑģобноÑģÑĤÑĮ
    -0.08
    ÑģпоÑģобноÑģÑĤи
    -0.08
    สà¹Į
    -0.08
    æĽ´æĸ°äºİ
    -0.08
    ï¾Ł
    -0.08
    ters
    -0.08
    گاÙĩ
    -0.08
    POSITIVE LOGITS
    aceous
    0.09
    inh
    0.08
     маÑģлом
    0.07
    uality
    0.06
    eri
    0.06
    ذاÙĥ
    0.06
    ³
    0.06
    ually
    0.06
    ories
    0.06
    antry
    0.06
    Activations Density 0.068%

    No Known Activations