© 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. 22487
    Prev
    Next
    INDEX
    Explanations

    multiobjective formulation, ivalency, nonrigid, surveys

    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
     tyt
    -0.08
    ä¼İ
    -0.08
     Ogg
    -0.08
    osz
    -0.08
    ossa
    -0.08
     Suomi
    -0.08
    éłĨ
    -0.08
    åīį款
    -0.08
    adero
    -0.07
    ç»ĪæĹ¥
    -0.07
    POSITIVE LOGITS
     fuzzy
    0.13
    uzzy
    0.12
    模ç³Ĭ
    0.09
     fuzz
    0.08
     má»Ŀ
    0.08
    values
    0.07
     values
    0.07
     ratings
    0.07
    lood
    0.07
    Soft
    0.07
    Activations Density 0.010%

    No Known Activations