© 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. 17957
    Prev
    Next
    INDEX
    Explanations

    theatre and acting training

    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
    ÑĤал
    -0.07
    ool
    -0.06
    ç¡ķ
    -0.06
    almaz
    -0.06
     hike
    -0.06
     comun
    -0.06
    endale
    -0.06
    é¥®é£Łä¸Ĭ
    -0.06
    iband
    -0.06
     omin
    -0.06
    POSITIVE LOGITS
    表æ¼ĶçļĦ
    0.11
    æ¼ĶçļĦ
    0.11
     ÑĤеаÑĤÑĢа
    0.10
    actors
    0.10
    表æ¼Ķ
    0.10
     поÑģÑĤанов
    0.10
    mime
    0.10
    ç²¾æ¹ĽçļĦ
    0.10
    å¹ķ
    0.09
     teatra
    0.09
    Activations Density 0.194%

    No Known Activations