© 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. 2246
    Prev
    Next
    INDEX
    Explanations

    vertical measurements and extent

    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
    åIJĮç±»
    -0.08
    治水
    -0.08
    ream
    -0.08
    纯æŃ£
    -0.07
    Side
    -0.07
     Side
    -0.07
     side
    -0.07
    端éĿ¢
    -0.07
    Score
    -0.07
     Score
    -0.07
    POSITIVE LOGITS
    å±Ĥ
    0.15
    層
    0.14
     layers
    0.14
    layers
    0.13
    å±ĤçļĦ
    0.13
     layer
    0.13
    layer
    0.13
    .layer
    0.11
     depths
    0.11
    -layer
    0.11
    Activations Density 0.024%

    No Known Activations