© 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. 32333
    Prev
    Next
    INDEX
    Explanations

    versions or types

    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
    zol
    -0.07
    orne
    -0.07
    uss
    -0.07
    æĿ¥äºº
    -0.07
    éģ
    -0.06
    Wür
    -0.06
     Candidates
    -0.06
    åIJĮçIJĨ
    -0.06
    åħľ
    -0.06
    åĢĻéĢī
    -0.06
    POSITIVE LOGITS
     versions
    0.11
    çīĪæľ¬
    0.11
    çļĦçīĪæľ¬
    0.11
     variants
    0.11
     version
    0.10
     variante
    0.10
     variant
    0.10
    versions
    0.09
     editions
    0.09
     varian
    0.09
    Activations Density 0.538%

    No Known Activations