© 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. 55395
    Prev
    Next
    INDEX
    Explanations

    market movements and price changes

    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
    .abort
    -0.07
    å¾Ĺ罪
    -0.07
    æĬķèµĦæĪĸæݧèĤ¡
    -0.07
    èŀįèµĦåİĨç¨ĭ
    -0.07
    éĽ
    -0.07
    æĬķèµĦäºĭ件
    -0.06
    çĭ¬èµĦ
    -0.06
    å®ŀç¼´åĩºèµĦé¢Ŀ
    -0.06
    åįĩæģ¯
    -0.06
    å¤ĸåĮħ
    -0.06
    POSITIVE LOGITS
    çļĦèµ°åĬ¿
    0.10
     volatility
    0.10
    èµ°åĬ¿
    0.10
     Mov
    0.10
     rally
    0.10
     movements
    0.09
    æĥħ绪
    0.09
     rallies
    0.09
     ticker
    0.09
     bullish
    0.09
    Activations Density 0.214%

    No Known Activations