© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    consecutive words or numbers

    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
    è§Ĩéķľ
    -0.09
    人æĥħ
    -0.08
    年代åĪĿ
    -0.08
    èģĶæݧ
    -0.07
    icap
    -0.07
    _dummy
    -0.07
    icoli
    -0.07
    eroy
    -0.07
    leep
    -0.07
    urch
    -0.07
    POSITIVE LOGITS
    æģ°å·§
    0.11
    æģ°å¥½
    0.10
     simultaneously
    0.09
    å·§åIJĪ
    0.08
    çļĦå®Įç¾İ
    0.08
     ëıĻìĭľìĹIJ
    0.07
    åIJĮæŶ
    0.07
     одновÑĢеменно
    0.07
    æģ°
    0.07
    纯æŃ£
    0.07
    Activations Density 0.104%

    No Known Activations