© 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. 25686
    Prev
    Next
    INDEX
    Explanations

    of various scientific measurements

    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
    apol
    -0.09
    ruhe
    -0.08
     altogether
    -0.07
    uston
    -0.07
    æ¦Ĥæĭ¬
    -0.07
    adaran
    -0.07
    ewhat
    -0.07
    siasi
    -0.07
    è·ŁæĪij们
    -0.07
    ợ
    -0.07
    POSITIVE LOGITS
    .pdf
    0.08
     terde
    0.06
    ìĦĿ
    0.06
     versus
    0.06
    åĨįçĶ¨
    0.06
    cop
    0.06
     Cy
    0.06
     |
    0.06
    丨
    0.06
     ld
    0.06
    Activations Density 3.975%

    No Known Activations