© 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. 30203
    Prev
    Next
    INDEX
    Explanations

    heterogeneous spatial distribution variability

    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
    .release
    -0.07
    мино
    -0.07
    ymar
    -0.07
    à¸Ĺà¸Ķ
    -0.07
     lá»ģ
    -0.07
    æ¸ħ空
    -0.06
    åħŃåIJĪ
    -0.06
    ardi
    -0.06
    æIJŃä¸Ĭ
    -0.06
    uard
    -0.06
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.18
     distribution
    0.16
    ä¸įåĿĩåĮĢ
    0.16
    ä¸įåĿĩ
    0.14
    distribution
    0.14
     Distribution
    0.14
    Distribution
    0.13
     spatial
    0.13
     uneven
    0.13
     regions
    0.13
    Activations Density 0.195%

    No Known Activations