© 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. 19680
    Prev
    Next
    INDEX
    Explanations

    number sequences like -1

    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
    ewise
    -0.09
    lauf
    -0.08
    ë°ĸ
    -0.07
    à¹Ĩ
    -0.07
    ieza
    -0.07
    menos
    -0.07
    ä¹ĭ大
    -0.07
    Ĺı
    -0.07
    aining
    -0.07
    ekar
    -0.06
    POSITIVE LOGITS
    /-
    0.08
    /+
    0.08
    ç®Ģ书
    0.07
    转æŃ£
    0.07
    аÑĤег
    0.07
    elige
    0.07
    /--
    0.06
    ighbour
    0.06
    ighted
    0.06
    ึà¹īà¸ĩ
    0.06
    Activations Density 0.056%

    No Known Activations