© 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. 16651
    Prev
    Next
    INDEX
    Explanations

    singles and vice president

    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
    anyon
    -0.09
    angu
    -0.08
    anja
    -0.08
    λοÏį
    -0.07
    ä¸įåħī
    -0.07
    ç¬¬åĽĽåŃ£
    -0.07
     fitte
    -0.07
    åĸ¶
    -0.07
     Nego
    -0.07
    交æµģä¼ļ
    -0.07
    POSITIVE LOGITS
    osat
    0.07
    onte
    0.07
    roe
    0.06
    æļĤè¡Į
    0.06
    寨
    0.06
    OST
    0.06
    Âł
    0.06
     combination
    0.06
    Ether
    0.06
    èĢĥåĭ¤
    0.06
    Activations Density 0.001%

    No Known Activations