© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    display / visualization

    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
    ç½ijç«Ļ导èĪª
    -0.08
     parten
    -0.07
    ä¼Łå¤§çļĦ
    -0.07
     stuffing
    -0.07
    ãĥ¼ãĤ¯
    -0.07
    embr
    -0.06
    .submit
    -0.06
    ebu
    -0.06
    ultipartFile
    -0.06
     hasard
    -0.06
    POSITIVE LOGITS
    æĺ¾ç¤º
    0.15
     displays
    0.14
     display
    0.13
     displaying
    0.13
    æĺ¾ç¤ºçļĦ
    0.13
     displayed
    0.13
    顯示
    0.13
     Displays
    0.12
    å®ŀæŶ
    0.12
     оÑĤобÑĢа
    0.12
    Activations Density 0.554%

    No Known Activations