© 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. 12181
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting

    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
    Ĩ
    -0.08
    å¦ĥ
    -0.07
    fine
    -0.07
     Meine
    -0.07
    gant
    -0.07
    Ĺ
    -0.07
    为贯彻èIJ½å®ŀ
    -0.07
    *M
    -0.07
    zyman
    -0.06
    _TASK
    -0.06
    POSITIVE LOGITS
    atile
    0.08
    otella
    0.07
    çī©åĴĮ
    0.07
    водом
    0.07
    ç¼ĸèĢħ
    0.07
     nguyá»ĩt
    0.06
    æĬĦ
    0.06
    æľ¨æľī
    0.06
    饶
    0.06
     orario
    0.06
    Activations Density 0.006%

    No Known Activations