© 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. 10110
    Prev
    Next
    INDEX
    Explanations

    groups and experimental conditions

    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
    brook
    -0.07
    ewn
    -0.07
    ivia
    -0.07
    æľ¬èº«çļĦ
    -0.07
    unless
    -0.07
    ä¾ĿçĦ¶
    -0.07
    except
    -0.07
    çħ§æł·
    -0.07
     Finally
    -0.07
    åIJĮæł·
    -0.07
    POSITIVE LOGITS
    åĪĻéľĢè¦ģ
    0.08
    ãģĿãģĨãģ§
    0.07
    flate
    0.07
    ÛĮدÛĮ
    0.07
    åĪĻæľī
    0.07
    åĪĻ表示
    0.07
    é½IJæĬĵ
    0.07
    åį´å¾Ī
    0.07
    arend
    0.07
    éĽªçĻ½çļĦ
    0.07
    Activations Density 0.155%

    No Known Activations