© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    Game of Thrones

    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
    æ¥
    -0.07
    tsx
    -0.07
     prek
    -0.07
    edef
    -0.06
     Volta
    -0.06
    Decision
    -0.06
     hal
    -0.06
    å¾Ĵ
    -0.06
    æī«ä¸Ģæī«
    -0.06
    erima
    -0.06
    POSITIVE LOGITS
     insp
    0.08
    Jets
    0.08
     Hayden
    0.08
    Jet
    0.08
     Jets
    0.08
    iclet
    0.07
     Mald
    0.07
     hep
    0.07
    大家æĹı
    0.07
    åłĨ
    0.07
    Activations Density 0.013%

    No Known Activations