© 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. 11471
    Prev
    Next
    INDEX
    Explanations

    public speaking and addresses

    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
    çĭĹä»Ķ
    -0.08
    ç»ĵä¼´
    -0.07
    èģļä¼ļ
    -0.07
    .setdefault
    -0.07
    æīĭä¼Ŀ
    -0.07
    snap
    -0.07
    á»Ŀ
    -0.07
     screenshot
    -0.07
    好äºĭ
    -0.07
     Umg
    -0.07
    POSITIVE LOGITS
     speeches
    0.11
    æ¼Ķ讲
    0.10
    æ¿ĢæĺĤ
    0.09
    讲解
    0.09
    讲çļĦ
    0.09
     speech
    0.09
    ç»ĵæĿŁåIJİ
    0.09
    讲äºĨ
    0.09
     delivering
    0.09
    讲è¯Ŀ
    0.09
    Activations Density 0.442%

    No Known Activations