© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    world war history

    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
    大åįĥ
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    lix
    -0.07
     künftig
    -0.07
    åľ¨æĹ¥å¸¸
    -0.07
    ä»ĬåIJİçļĦ
    -0.07
     Eller
    -0.07
     sợ
    -0.07
    èĿł
    -0.07
    临åºĬ
    -0.07
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.13
     timeline
    0.12
     historians
    0.12
    åľ¨æŃ¤æľŁéĹ´
    0.12
    å½ĵæŶ
    0.12
    åIJĮæľŁçļĦ
    0.11
    å½ĵæĻĤãģ®
    0.11
     Timeline
    0.11
    timeline
    0.11
    åı²æĸĻ
    0.11
    Activations Density 0.441%

    No Known Activations