© 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. 60446
    Prev
    Next
    INDEX
    Explanations

    random, json, math imports

    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
    à¸ĩ
    -0.09
    θεν
    -0.09
    åĬ¨åĬ¨
    -0.08
    wiad
    -0.08
     Guten
    -0.08
    $__
    -0.08
    åºĵéĩĮ
    -0.08
    <|repo_name|>
    -0.08
    ivin
    -0.07
    ereum
    -0.07
    POSITIVE LOGITS
    ize
    0.07
    庵
    0.07
    ably
    0.06
    ijkstra
    0.06
    çħ
    0.06
    é²ľ
    0.06
    åħ¨éĥ¨çļĦ
    0.06
    _wrapper
    0.06
    -s
    0.06
    s
    0.06
    Activations Density 0.003%

    No Known Activations