© 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. 42130
    Prev
    Next
    INDEX
    Explanations

    hedging and short positions

    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
    åĪĨåĮº
    -0.09
    å°Ķåħĭ
    -0.08
    éĤĥ
    -0.08
    å·¥ä½ľçļĦéĩįè¦ģ
    -0.07
    æīĢæľª
    -0.07
    emez
    -0.07
    çł
    -0.07
    åĬŁèĥ½åĮº
    -0.07
     exceptions
    -0.07
    inea
    -0.07
    POSITIVE LOGITS
    å®ŀçī©
    0.08
     hedge
    0.07
     holdings
    0.07
    æľŁåĪĿ
    0.07
    æĮģæľīçļĦ
    0.07
    combination
    0.07
    æĬµ
    0.07
    ç»ĦåIJĪ
    0.07
     combination
    0.07
    æIJŃ
    0.07
    Activations Density 0.006%

    No Known Activations