© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    chromatography or mathematical formulas

    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
    MT
    -0.07
    _COMPILE
    -0.07
    اÛĮÛĮ
    -0.07
    åŃĹ第
    -0.07
    麻麻
    -0.07
    .defaults
    -0.07
    oric
    -0.07
    kers
    -0.07
    KR
    -0.07
    alan
    -0.06
    POSITIVE LOGITS
    æĻĵ举
    0.07
    enge
    0.07
    ÑĤоÑĢи
    0.07
     altogether
    0.07
    ä½µ
    0.07
    lew
    0.06
    订éĺħä¸ĵæłı
    0.06
    éĩij森
    0.06
    èĶļ
    0.06
    begin
    0.06
    Activations Density 0.002%

    No Known Activations