© 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. 9920
    Prev
    Next
    INDEX
    Explanations

    density

    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
    strup
    -0.09
    ÙĬاء
    -0.08
    hatt
    -0.08
    gers
    -0.08
    åİħéķ¿
    -0.07
    bidden
    -0.07
     secco
    -0.07
    è¾Ļ
    -0.07
    nehm
    -0.07
    chend
    -0.07
    POSITIVE LOGITS
    нок
    0.11
    avenport
    0.08
    icken
    0.07
    à¸łà¸±à¸ĵà¸ijà¹Į
    0.07
    orsi
    0.07
    ourage
    0.07
    Ł
    0.07
    ctrine
    0.07
    YNAM
    0.07
    лÑĮкÑĥ
    0.07
    Activations Density 0.016%

    No Known Activations