© 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. 11604
    Prev
    Next
    INDEX
    Explanations

    April Fool's Day, trick, kidding, pitfalls

    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
    çķ´
    -0.08
    éľĨ
    -0.07
    ACHINE
    -0.07
    ç°ĩ
    -0.07
    å±ķ
    -0.07
    å¾Ĺèµ·
    -0.07
    ẽ
    -0.07
    æĺ¨
    -0.07
    tems
    -0.07
    èĩªåıij
    -0.07
    POSITIVE LOGITS
    æķħæĦı
    0.11
    éĻ·éĺ±
    0.10
     intentionally
    0.09
     purposely
    0.08
     Tricks
    0.08
    è¯Ī
    0.08
     deceptive
    0.07
     question
    0.07
     deliberately
    0.07
    误导
    0.07
    Activations Density 0.012%

    No Known Activations