© 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. 11346
    Prev
    Next
    INDEX
    Explanations

    image segmentation

    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
     Plain
    -0.07
    åij³éģĵ
    -0.07
    _ipv
    -0.06
     shuffle
    -0.06
    heim
    -0.06
    atter
    -0.06
    秸
    -0.06
    _dom
    -0.06
     Mix
    -0.06
     mixing
    -0.06
    POSITIVE LOGITS
     blobs
    0.10
    åĪĴå®ļ
    0.10
     segmentation
    0.09
    semantic
    0.09
    accur
    0.09
     boundaries
    0.09
     extraction
    0.09
     accuracy
    0.09
    extract
    0.09
    BoundingBox
    0.09
    Activations Density 0.150%

    No Known Activations