© 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. 49634
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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
    Ùģت
    -0.08
    å¥½ä¸ľè¥¿
    -0.08
    ebes
    -0.07
    althy
    -0.07
    LOTS
    -0.07
    дов
    -0.07
    opers
    -0.07
    itÃł
    -0.07
    ÙģتÙĩ
    -0.07
    AVIS
    -0.07
    POSITIVE LOGITS
    uary
    0.08
    ique
    0.07
    'Neill
    0.07
    ieri
    0.07
    à¥įय
    0.07
    zee
    0.07
    vertime
    0.07
    acha
    0.07
    meal
    0.07
    yno
    0.07
    Activations Density 0.027%

    No Known Activations