© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    television and TV shows

    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
     TripAdvisor
    -0.07
    åıijç»Ļ
    -0.07
    ington
    -0.07
    åĿļå®ŀçļĦ
    -0.07
    å¾Ĺ天çĭ¬
    -0.07
    è¡Įä¹ĭ
    -0.07
    boro
    -0.06
    累累
    -0.06
    ikum
    -0.06
    ÑģÑĭпаÑĤÑĮ
    -0.06
    POSITIVE LOGITS
     television
    0.10
    æĶ¶è§Ĩçİĩ
    0.09
     TV
    0.09
     Television
    0.09
    -TV
    0.09
    鼻è¦ĸ
    0.09
    çĶµè§Ĩ
    0.09
    æĶ¶çľĭ
    0.09
    æĶ¶è§Ĩ
    0.08
     televis
    0.08
    Activations Density 0.122%

    No Known Activations