© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    sayings and proverbs

    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
    öt
    -0.07
    鬼
    -0.07
    åĪ°ä¸Ģ个
    -0.07
    ä¸½å¨ľ
    -0.07
    åĩ¤
    -0.07
    ä¸Ģ说
    -0.07
    åĪ°ä½İ
    -0.07
    mittag
    -0.07
    wart
    -0.06
    anness
    -0.06
    POSITIVE LOGITS
    åħ®
    0.09
    éªĦéĺ³
    0.07
    ä¸įåİĮ
    0.07
    æĶĺ
    0.07
    skr
    0.07
    astra
    0.07
    åĽ½å¼º
    0.06
    xxxx
    0.06
    audi
    0.06
    æľĶ
    0.06
    Activations Density 0.061%

    No Known Activations