© 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. 33255
    Prev
    Next
    INDEX
    Explanations

    commas preceding mathematical variables

    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
    ÄĽst
    -0.07
    anea
    -0.07
    kk
    -0.07
    她就æĺ¯
    -0.07
    ered
    -0.07
    æĢ§ä¸İ
    -0.07
    就没æľī
    -0.06
    请ä¸İ
    -0.06
    èĭ¥å¹²éĹ®é¢ĺçļĦ解éĩĬ
    -0.06
    ä¸İä¼łç»Ł
    -0.06
    POSITIVE LOGITS
    ãģ¨ãĤĤãģ«
    0.11
     themselves
    0.10
    åħ±ãģ«
    0.10
    ä¹ĭåĪ«
    0.08
    åIJĦæľī
    0.07
    ä¹ĭ交
    0.07
    åĪĨåĪ«æĺ¯
    0.07
    _are
    0.07
    ä¸Ģä½ĵçļĦ
    0.07
    é¾Ļä¹ĭ
    0.07
    Activations Density 0.007%

    No Known Activations