© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16943
    Prev
    Next
    INDEX
    Explanations

    package.json keys and structure

    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
    obet
    -0.09
    terior
    -0.08
    ä¸Ģç§Ĵ
    -0.08
    dbl
    -0.08
    æĺ¯ä¸įå¤Ł
    -0.08
    ordes
    -0.08
    owell
    -0.08
    sius
    -0.08
    enerd
    -0.07
    Dup
    -0.07
    POSITIVE LOGITS
    zn
    0.07
    _requires
    0.06
    å¡ļ
    0.06
    ro
    0.06
    æĽĻåħī
    0.06
    éĴ
    0.06
    åįģåŃĹ
    0.06
     Kek
    0.06
    æ¯Ĵ
    0.06
    зна
    0.06
    Activations Density 0.014%

    No Known Activations