© 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. 40654
    Prev
    Next
    INDEX
    Explanations

    shapes and structures

    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
    _trampoline
    -0.09
    lott
    -0.08
    ç«ŀäºīé£İéĻ©
    -0.08
    atriz
    -0.08
    æĢ§ä»·
    -0.08
    å¸ĤéĿ¢ä¸ĬçļĦ
    -0.08
    éĢļè¿ĩ以ä¸Ĭ
    -0.08
    (Role
    -0.07
    ä¹ĭåīij
    -0.07
    gulp
    -0.07
    POSITIVE LOGITS
    aho
    0.07
    uro
    0.07
    èį·
    0.06
    ék
    0.06
    éĩĩ
    0.06
     Lor
    0.06
    çķĮ
    0.05
     Hudson
    0.05
    å¦Ļ
    0.05
    æľīåĪ©äºİ
    0.05
    Activations Density 0.220%

    No Known Activations