© 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. 16320
    Prev
    Next
    INDEX
    Explanations

    Gaussian mixture models

    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
    bord
    -0.08
    ocken
    -0.07
    rane
    -0.07
    tes
    -0.07
    _unused
    -0.07
    dims
    -0.07
    leta
    -0.07
     BÃłn
    -0.06
    ä¸Ģè½®
    -0.06
     prov
    -0.06
    POSITIVE LOGITS
     mixture
    0.10
    æ··åIJĪ
    0.10
     ÑģмеÑģи
    0.10
    ĥĿ
    0.09
    .mix
    0.09
    union
    0.09
     membership
    0.08
     mixing
    0.08
     ÑģмеÑģÑĮ
    0.08
    _union
    0.08
    Activations Density 0.023%

    No Known Activations