© 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. 22210
    Prev
    Next
    INDEX
    Explanations

    individual things

    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
    /Foundation
    -0.07
    éĹ®é¢ĺåĪĨæŀIJ
    -0.07
    ucie
    -0.07
    விலà¯į
    -0.07
    quist
    -0.07
    haf
    -0.07
    ÅĽle
    -0.07
    ганÑĤ
    -0.07
    ensch
    -0.07
    utsch
    -0.07
    POSITIVE LOGITS
    缴æİ¥åħ³ç³»åĪ°
    0.10
    缴æݥ影åĵį
    0.10
    缴æݥ影åĵįåĪ°
    0.10
     physical
    0.08
    缴æİ¥çļĦ
    0.08
    åı¯ä»¥çĽ´æİ¥
    0.08
     directly
    0.08
    缴æİ¥ä¸İ
    0.08
    çī©çIJĨ
    0.07
    ä¸įåĥı
    0.07
    Activations Density 0.098%

    No Known Activations