© 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. 58429
    Prev
    Next
    INDEX
    Explanations

    data structure algorithms

    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
    _secure
    -0.07
    untu
    -0.07
    èĢĮ论
    -0.06
    fels
    -0.06
    ouser
    -0.06
    ä¹±æĶ¾
    -0.06
    æľ¬ç«ł
    -0.06
    inness
    -0.06
    oltip
    -0.06
    åİ®
    -0.06
    POSITIVE LOGITS
    -lite
    0.10
    æĢĿæĥ³
    0.08
    gist
    0.08
    ãĤ®ãĥ£
    0.08
    loyd
    0.07
    lify
    0.07
    å½ĴæĿ¥
    0.07
    (Pointer
    0.07
    çģ¿
    0.07
    -style
    0.07
    Activations Density 0.050%

    No Known Activations