© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    Fight Club, GIG distribution, SIR model, Hydra

    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
    æīĺ
    -0.07
    .VERSION
    -0.06
    cking
    -0.06
    好æ¯Ķ
    -0.06
    ä¸Ģå±Ĥ
    -0.06
     voilÃł
    -0.06
    gat
    -0.06
    ilty
    -0.06
    ç¡ķ士çĶŁ
    -0.06
    æ¯Ķèµ·
    -0.06
    POSITIVE LOGITS
    çļĦéĤ£æł·
    0.11
    éĤ£æł·
    0.10
    éĤ£æ¨£
    0.10
    ä¸įåIJĮçļĦæĺ¯
    0.09
    éĤ£èĪ¬
    0.09
    ä¹ŁåIJĮæł·
    0.08
    çŃīä¼łç»Ł
    0.08
     sebelumnya
    0.08
     similarly
    0.08
     ähnliche
    0.08
    Activations Density 0.580%

    No Known Activations