© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2901
    Prev
    Next
    INDEX
    Explanations

    religious and spiritual leaders

    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
    è·ĥè·ĥ
    -0.08
     ná»Ļp
    -0.07
    éĹ®å¥½
    -0.07
     пÑĢеÑĤен
    -0.07
    oust
    -0.07
    licant
    -0.07
    -webpack
    -0.06
    衬æīĺ
    -0.06
     EXEC
    -0.06
     familiare
    -0.06
    POSITIVE LOGITS
     teachings
    0.11
     impart
    0.10
    æķĻ导
    0.09
    åľ¨ä¸ĸ
    0.09
    ä¼Łå¤§
    0.09
    å¼ŁåŃIJ
    0.09
    亲èĩª
    0.09
     dạy
    0.09
    è¨Ģä¼ł
    0.09
     instruct
    0.08
    Activations Density 0.093%

    No Known Activations