© 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. 61155
    Prev
    Next
    INDEX
    Explanations

    citations in scientific papers

    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
    aline
    -0.08
    ério
    -0.08
     Saturdays
    -0.07
    ardia
    -0.07
    olat
    -0.07
    engar
    -0.07
    å¾Ĵ
    -0.07
    াà¦ģ
    -0.07
    æĭį
    -0.07
    æĸĩæѦ
    -0.07
    POSITIVE LOGITS
    cep
    0.07
    ber
    0.06
    æľīåħ³äºİ
    0.06
    æĸ¹æ³ķæĿ¥
    0.06
    sterdam
    0.06
    ÑĨей
    0.06
    باب
    0.06
    ä¸Ĭ说
    0.06
    sted
    0.06
    anta
    0.06
    Activations Density 0.168%

    No Known Activations