© 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. 58128
    Prev
    Next
    INDEX
    Explanations

    stored procedure definition

    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
    asiun
    -0.08
    кÑĤи
    -0.07
     Moment
    -0.07
    ç·Ĵ
    -0.07
    Moment
    -0.07
    rophe
    -0.07
    件çļĦ
    -0.07
    çĹĩçļĦ
    -0.07
    racle
    -0.07
    ifact
    -0.07
    POSITIVE LOGITS
    çİĭä¹ĭ
    0.07
    ÑĬ
    0.07
    oven
    0.07
    omme
    0.07
    CONTEXT
    0.07
    apo
    0.07
    åijĥ
    0.06
    åĴ¨è¯¢æľīéĻIJåħ¬åı¸
    0.06
    ä¸į好äºĨ
    0.06
    篮
    0.06
    Activations Density 0.008%

    No Known Activations