© 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. 21993
    Prev
    Next
    INDEX
    Explanations

    mathematics and acronyms

    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
    enska
    -0.10
    æģ©æĸ¯
    -0.09
    eria
    -0.08
    arca
    -0.08
    .loaded
    -0.07
    æĤħ
    -0.07
    å»¶è¿Ł
    -0.07
    å¤§æľ¬
    -0.07
     greve
    -0.07
    .Ultra
    -0.07
    POSITIVE LOGITS
    Haz
    0.06
    Ïĥιμο
    0.06
    ifiant
    0.06
    'd
    0.06
    oder
    0.06
     Teixeira
    0.06
    å¾ĪéĢĤåIJĪ
    0.06
    .te
    0.06
    æĺ¯å¯¼èĩ´
    0.06
    å¾Ļ
    0.06
    Activations Density 0.002%

    No Known Activations