© 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. 60929
    Prev
    Next
    INDEX
    Explanations

    a, numbers, and symbols

    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
    ota
    -0.07
    ptron
    -0.07
     perdana
    -0.07
    馴
    -0.07
    #c
    -0.07
    .getLog
    -0.07
    uzzle
    -0.07
    fahr
    -0.07
    _FA
    -0.06
     exhaus
    -0.06
    POSITIVE LOGITS
     scaling
    0.09
    èĦĬ
    0.09
    缩
    0.09
     Scaling
    0.08
    æ¯Ķä¾ĭ
    0.08
    quera
    0.08
    scaling
    0.08
    ä¹ĭæ¯Ķ
    0.07
     Secondary
    0.07
     ratio
    0.07
    Activations Density 0.040%

    No Known Activations