© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    website / web pages

    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
    ÑģÑĭпаÑĤÑĮ
    -0.07
    dbus
    -0.07
     Kinect
    -0.07
    èĨı
    -0.07
    太è¡Į
    -0.07
    çĥŃéŨæłĩçŃ¾
    -0.07
     rangement
    -0.07
    åľºä¸Ĭ
    -0.07
    微信åı·
    -0.07
    äºijå³°
    -0.07
    POSITIVE LOGITS
     HTML
    0.12
     crawl
    0.11
     web
    0.11
     favicon
    0.11
     URLs
    0.10
     HTTP
    0.10
     visitor
    0.10
    crawl
    0.10
     URL
    0.10
    page
    0.10
    Activations Density 1.842%

    No Known Activations