© 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. 13581
    Prev
    Next
    INDEX
    Explanations

    register transfer or intersection

    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
    ataka
    -0.08
    _AUD
    -0.08
    ilenames
    -0.07
    ryw
    -0.07
    lui
    -0.07
    èĢ³é¼»åĸī
    -0.07
    UNDLE
    -0.07
     colectiv
    -0.07
    ————————————————
    -0.07
    conds
    -0.07
    POSITIVE LOGITS
     or
    0.06
    Å¡Äį
    0.06
    交æµģåĴĮ
    0.06
    æľīçIJĨ
    0.06
    è¾ĥéĩı
    0.06
    æݥ触çļĦ
    0.06
    inggu
    0.06
     interface
    0.06
     matchup
    0.06
    æīĵ交éģĵ
    0.06
    Activations Density 0.033%

    No Known Activations