© 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. 56664
    Prev
    Next
    INDEX
    Explanations

    object or array indexing

    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
     hale
    -0.08
    bound
    -0.07
    丼
    -0.07
    ritch
    -0.07
    åĮł
    -0.07
    ç§ĭæĹ¥
    -0.07
    éģĵéģĵ
    -0.07
    hta
    -0.07
    cene
    -0.07
    åľŃ
    -0.07
    POSITIVE LOGITS
    prises
    0.08
    ujan
    0.07
    spath
    0.07
    alus
    0.07
    .promise
    0.07
    åIJįåŁİ
    0.06
    çļĻ
    0.06
     prêt
    0.06
    çĵ¤
    0.06
    ukup
    0.06
    Activations Density 0.195%

    No Known Activations