© 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. 57599
    Prev
    Next
    INDEX
    Explanations

    C++ include Eigen

    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
    麹
    -0.07
    kening
    -0.07
    è¿Ľè¡Įä¿®æĶ¹
    -0.07
    (forKey
    -0.07
    retta
    -0.06
    igator
    -0.06
    'av
    -0.06
    due
    -0.06
    åłĢ
    -0.06
    /framework
    -0.06
    POSITIVE LOGITS
    μμα
    0.07
    Thread
    0.07
    æĥ°
    0.07
    ìĪł
    0.07
    æľ«
    0.07
    æĿ¥æİ¥
    0.07
    å¾ĢæĺĶ
    0.07
    ãĥ¬ãĥ¼ãĥī
    0.07
    ework
    0.07
    ettel
    0.07
    Activations Density 0.002%

    No Known Activations