© 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. 47912
    Prev
    Next
    INDEX
    Explanations

    [auto_generated][WE[DOB

    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
    voud
    -0.09
    ight
    -0.08
    gether
    -0.08
    edio
    -0.07
    perature
    -0.07
    hower
    -0.07
    мили
    -0.07
    джа
    -0.07
    нови
    -0.07
    ÑĮми
    -0.07
    POSITIVE LOGITS
    s
    0.11
    ات
    0.11
    两åѦä¸Ģåģļ
    0.10
    缸è¾ħ缸æĪIJ
    0.10
    sic
    0.09
    ×Ļ×Ŀ
    0.09
    人æĪĸ
    0.09
    о
    0.09
    sWith
    0.09
    身临åħ¶å¢ĥ
    0.08
    Activations Density 0.166%

    No Known Activations