© 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. 18871
    Prev
    Next
    INDEX
    Explanations

    gaps, spots, drops, folds, space

    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
    ashed
    -0.07
    å¾Ģ
    -0.07
    geh
    -0.07
    弥漫
    -0.06
    ÑĤÑĤ
    -0.06
     Jord
    -0.06
    éºĵ
    -0.06
     Geh
    -0.06
    ä¸įè¿ĺ
    -0.06
    urator
    -0.06
    POSITIVE LOGITS
    éģĹæ¼ı
    0.11
    æŃ»è§Ĵ
    0.11
    æ¼ı
    0.10
    éļĻ
    0.09
    åĴĮä¸į足
    0.09
    ugu
    0.09
    è§ĴèIJ½
    0.09
    个åĪ«
    0.09
     sót
    0.09
    ç®ĩæīĢ
    0.08
    Activations Density 0.045%

    No Known Activations