© 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. 18797
    Prev
    Next
    INDEX
    Explanations

    programming concepts container

    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
    umon
    -0.08
    ateria
    -0.07
     sedi
    -0.07
    tori
    -0.07
    .forRoot
    -0.07
     universally
    -0.07
    umé
    -0.06
    otype
    -0.06
    _Main
    -0.06
    大æľī
    -0.06
    POSITIVE LOGITS
     within
    0.14
    within
    0.14
     внÑĥÑĤÑĢи
    0.13
     innerhalb
    0.13
     Within
    0.13
    Within
    0.12
     dentro
    0.12
     inside
    0.12
    нÑĥÑĤÑĢи
    0.10
    à¸łà¸²à¸¢à¹ĥà¸Ļ
    0.10
    Activations Density 0.290%

    No Known Activations