© 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. 25220
    Prev
    Next
    INDEX
    Explanations

    acceleration and accelerometers

    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
    itsu
    -0.09
    zelf
    -0.08
    yard
    -0.08
    azer
    -0.08
    ÅĽ
    -0.08
    elijke
    -0.08
    eki
    -0.07
    ždy
    -0.07
    Ø©
    -0.07
    ä¿©
    -0.07
    POSITIVE LOGITS
    atriz
    0.09
    uated
    0.09
    /de
    0.08
    ments
    0.08
    ademia
    0.08
    รัà¸Ķ
    0.08
    миÑı
    0.08
    度çļĦ
    0.07
    ernt
    0.07
    umn
    0.07
    Activations Density 0.013%

    No Known Activations