© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30370
    Prev
    Next
    INDEX
    Explanations

    product average, kron

    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
    keypress
    -0.06
    é«ĺ度
    -0.06
    .Must
    -0.06
    oya
    -0.06
    éļĶ
    -0.06
    ç·Ĵ
    -0.06
    رØŃ
    -0.06
    umbo
    -0.06
    ars
    -0.06
    ewan
    -0.06
    POSITIVE LOGITS
    shine
    0.08
    æݢ头
    0.07
     Casal
    0.07
    ween
    0.07
     Brows
    0.07
    _CA
    0.07
    enius
    0.07
    xCD
    0.07
    åĽ½æŃĮ
    0.07
    举è¡Ĺ
    0.07
    Activations Density 0.008%

    No Known Activations