© 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. 65389
    Prev
    Next
    INDEX
    Explanations

    electric cars, hybrid vehicles

    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
     enactment
    -0.07
    utin
    -0.07
    nad
    -0.06
    éºŁ
    -0.06
    बà¥į
    -0.06
    dj
    -0.06
    na
    -0.06
    临
    -0.06
    dav
    -0.06
    .over
    -0.06
    POSITIVE LOGITS
    essus
    0.08
    ÃŃcio
    0.07
    ее
    0.07
    ео
    0.07
    ело
    0.07
     íĥĢìĿ´
    0.07
    lessly
    0.07
    leys
    0.07
    Ùħائ
    0.07
    ades
    0.07
    Activations Density 0.602%

    No Known Activations