© 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. 22622
    Prev
    Next
    INDEX
    Explanations

    ellipsis or bracket followed by text

    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
    lise
    -0.09
    elpers
    -0.08
    impse
    -0.08
     célib
    -0.08
    ivre
    -0.08
    ç«£
    -0.08
    ifecycle
    -0.08
    å¦Ĥåħ¶
    -0.08
    Pocket
    -0.08
    (AT
    -0.08
    POSITIVE LOGITS
    ot
    0.07
     bul
    0.07
    æķ£
    0.07
    æݨ
    0.06
    yt
    0.06
    交æµģ
    0.06
     [
    0.06
    obat
    0.06
    eder
    0.06
    åIJĦç§įåIJĦæł·
    0.06
    Activations Density 0.043%

    No Known Activations