© 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. 41538
    Prev
    Next
    INDEX
    Explanations

    Gallup transaction

    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
    çIJ¥
    -0.08
    nitz
    -0.08
    ×Ļף
    -0.07
    ÑĥÑģка
    -0.07
    íģ
    -0.07
    anine
    -0.07
    omes
    -0.07
     Fonse
    -0.07
    æıIJé«ĺèĩªèº«
    -0.07
    istani
    -0.07
    POSITIVE LOGITS
    ermo
    0.07
     pel
    0.07
    ç«ŀ
    0.07
    ä¸ĩåIJį
    0.06
    åıł
    0.06
    .removeAll
    0.06
     mén
    0.06
    arr
    0.06
     rozs
    0.06
    /libs
    0.06
    Activations Density 0.001%

    No Known Activations