© 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. 49245
    Prev
    Next
    INDEX
    Explanations

    placeholder for blanks

    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
    е
    -0.07
    纷åijĪ
    -0.07
    es
    -0.07
    ей
    -0.07
    à¸Ļà¹Į
    -0.07
    ie
    -0.07
    intér
    -0.07
    ack
    -0.07
    ignment
    -0.07
    en
    -0.07
    POSITIVE LOGITS
    ATURE
    0.09
    -than
    0.08
    halb
    0.07
    iliz
    0.07
    ë§ģ
    0.07
    ÑĶм
    0.07
    trang
    0.07
    _lot
    0.07
    naire
    0.07
    etzungen
    0.07
    Activations Density 0.006%

    No Known Activations