© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    punctuations or verb endings

    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
    atch
    -0.07
    èºĩ
    -0.07
    edin
    -0.07
    大éªĤ
    -0.07
     behaviours
    -0.07
     оÑĢÑĥ
    -0.07
    ikip
    -0.06
    好æĦŁ
    -0.06
     Toolbox
    -0.06
    æĹłéĩı
    -0.06
    POSITIVE LOGITS
    æ¯Ķè¾ĥ
    0.07
     comparing
    0.07
     comparison
    0.07
    äºij彩
    0.07
    è¿ŀéĶģ
    0.07
    ulam
    0.07
     rhetorical
    0.07
     rhet
    0.07
    æ¯Ķä¸įä¸Ĭ
    0.07
    æݧ
    0.07
    Activations Density 0.080%

    No Known Activations