© 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. 60628
    Prev
    Next
    INDEX
    Explanations

    coefficient bounds

    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
    åĿĹ
    -0.08
    inance
    -0.08
    笼
    -0.07
    çĤĴèıľ
    -0.07
    æīĢ欲è¨Ģ
    -0.07
    åIJĦåĽ½çļĦ
    -0.06
    _SWITCH
    -0.06
    itas
    -0.06
    åºĬåŀ«
    -0.06
    /releases
    -0.06
    POSITIVE LOGITS
    æ´ŀåı£
    0.08
    桦
    0.08
     lac
    0.08
    æ´ŀ
    0.07
    Cookies
    0.07
    полÑı
    0.07
    å®īå¨ľ
    0.07
     dilat
    0.07
    quot
    0.07
     martin
    0.07
    Activations Density 0.037%

    No Known Activations