© 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. 1631
    Prev
    Next
    INDEX
    Explanations

    do you/i

    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
    roma
    -0.08
    elon
    -0.07
    raad
    -0.06
    chaffen
    -0.06
    izie
    -0.06
    ÅĽci
    -0.06
    :frame
    -0.06
    èĩ´
    -0.06
     NEL
    -0.06
     testName
    -0.06
    POSITIVE LOGITS
    å·¥æĪ¿
    0.08
    annes
    0.08
    ãĤ¤ãĤº
    0.07
    Ñĩок
    0.07
    Ñĩко
    0.07
    ØŃاÙĦ
    0.07
    oyer
    0.07
    ÙĪاء
    0.07
    ossal
    0.07
    fdc
    0.07
    Activations Density 0.003%

    No Known Activations