© 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. 40254
    Prev
    Next
    INDEX
    Explanations

    allowing permission

    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
    wab
    -0.08
    ÑĢÑıÑĤ
    -0.08
    bing
    -0.08
    ëĨĪ
    -0.07
    mailer
    -0.07
    lias
    -0.07
     Äijáo
    -0.07
    alytics
    -0.07
    سد
    -0.07
     Alte
    -0.07
    POSITIVE LOGITS
    ance
    0.10
    åĴĮé¼ĵåĬ±
    0.09
    ably
    0.08
    ances
    0.08
    anced
    0.08
    izia
    0.08
    itud
    0.08
    å°ijéĩı
    0.07
     unrestricted
    0.07
    ä¸įåIJĮç¨ĭ度çļĦ
    0.07
    Activations Density 0.062%

    No Known Activations