© 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. 41801
    Prev
    Next
    INDEX
    Explanations

    poisson distribution, model, regression

    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
     Ñģобой
    -0.08
    Ģ
    -0.08
    uator
    -0.08
    eloos
    -0.07
    ¼
    -0.07
    /disable
    -0.07
    amage
    -0.07
    tei
    -0.07
    fél
    -0.07
    عاد
    -0.07
    POSITIVE LOGITS
    /cms
    0.08
    ainen
    0.08
    ernen
    0.08
    igl
    0.07
    ern
    0.07
    elli
    0.07
    ekk
    0.07
    uille
    0.07
    kün
    0.07
    ambul
    0.07
    Activations Density 0.003%

    No Known Activations