© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14653
    Prev
    Next
    INDEX
    Explanations

    distribution

    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
    æĹłæģĻ
    -0.09
    idação
    -0.08
    δικ
    -0.08
    otos
    -0.08
    ONGL
    -0.08
    gris
    -0.08
    леÑĤней
    -0.08
    ORIES
    -0.08
    лÑİд
    -0.07
    ãģ£ãģįãĤĬ
    -0.07
    POSITIVE LOGITS
    ä¸įç»ı
    0.08
    pe
    0.07
     of
    0.07
    ÚĨÙĩ
    0.06
    eer
    0.06
    u
    0.06
    m
    0.06
    stuff
    0.06
    hani
    0.06
     mash
    0.06
    Activations Density 0.006%

    No Known Activations