© 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. 28057
    Prev
    Next
    INDEX
    Explanations

    degrees, percentages, and measurements

    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
    ìĸ¸
    -0.08
    enson
    -0.07
    à¸Łà¹īา
    -0.07
    linger
    -0.07
    åĽŃçļĦ
    -0.07
    atos
    -0.07
    åѦä¸ĵä¸ļ
    -0.06
    æĺłåħ¥çľ¼å¸ĺ
    -0.06
    ูà¹ī
    -0.06
    astian
    -0.06
    POSITIVE LOGITS
    ctor
    0.07
    rac
    0.07
    _unsigned
    0.06
    ten
    0.06
     thresholds
    0.06
    Dash
    0.06
    å°¸
    0.06
    éĿĵ
    0.06
    ìłľ
    0.06
    èĢIJä¹ħ
    0.06
    Activations Density 0.010%

    No Known Activations