© 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. 63471
    Prev
    Next
    INDEX
    Explanations

    special theory, ordinary differential, Old Testament, type 1 diabetes, Extended Kalman

    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
    iciel
    -0.08
    ÑĢÑıдка
    -0.08
    æ¼¾
    -0.08
    keer
    -0.08
    ymar
    -0.08
    ffy
    -0.07
    å¹´æĺ¥åŃ£
    -0.07
    poi
    -0.07
    rient
    -0.07
    heu
    -0.07
    POSITIVE LOGITS
    uan
    0.08
    unner
    0.07
    etos
    0.07
    atat
    0.07
     dealing
    0.06
    åѤ
    0.06
    æĹłæķĮ
    0.06
    ucker
    0.06
    æĹłåIJį
    0.06
    sid
    0.06
    Activations Density 0.005%

    No Known Activations