© 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. 63581
    Prev
    Next
    INDEX
    Explanations

    code arguments and types

    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
    OLLOW
    -0.07
    @if
    -0.07
    caret
    -0.06
    iby
    -0.06
    acz
    -0.06
    erness
    -0.06
    inite
    -0.06
    éry
    -0.06
    åľ¨ä»ĬåIJİçļĦ
    -0.06
    åŁŁçļĦ
    -0.06
    POSITIVE LOGITS
    uruan
    0.08
    ...',
    0.07
     [...
    0.07
    isan
    0.07
     (...)
    0.07
    ä¸įè¦ģè½»æĺĵ
    0.07
    ÅĨ
    0.07
    evat
    0.07
    æīĢ欲
    0.07
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    0.07
    Activations Density 0.001%

    No Known Activations