© 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. 40518
    Prev
    Next
    INDEX
    Explanations

    numbers followed by product

    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
    ate
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    odore
    -0.07
    -0.06
    ise
    -0.06
    anda
    -0.06
    èĩªå·±
    -0.06
    à°ĸ
    -0.06
    ur
    -0.06
    exels
    -0.06
    POSITIVE LOGITS
    /OR
    0.09
    OrElse
    0.09
    /or
    0.08
     Teixe
    0.08
    soever
    0.08
    orses
    0.08
    EEDED
    0.08
    reiz
    0.08
    âĤ¬“
    0.08
    panse
    0.08
    Activations Density 0.201%

    No Known Activations