© 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. 8266
    Prev
    Next
    INDEX
    Explanations

    patient or user

    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
    jaz
    -0.08
    ιά
    -0.08
    ÙĪÙĦÙĬÙĨ
    -0.07
    ohner
    -0.07
    æĺĻ
    -0.07
    ç®ĩ
    -0.07
    ìa
    -0.07
    为åŃ©åŃIJ们
    -0.07
    zeug
    -0.07
    iej
    -0.07
    POSITIVE LOGITS
    -side
    0.08
    -facing
    0.08
    /student
    0.08
    èĩ³ä¸Ĭ
    0.08
    /user
    0.08
    åĴĮä¼ģä¸ļ
    0.07
    _input
    0.07
     giò
    0.07
    说äºĨç®Ĺ
    0.07
     Terp
    0.07
    Activations Density 0.307%

    No Known Activations