© 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. 17481
    Prev
    Next
    INDEX
    Explanations

    financial losses or recovery

    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
    ople
    -0.07
    çĸijä¼¼è¿Ŀè§Ħ
    -0.07
     ideal
    -0.07
    çIJĨæĥ³
    -0.07
    ä¾Ľç»Ļ
    -0.07
    ideal
    -0.07
    ç¾²
    -0.07
    etty
    -0.07
    riet
    -0.06
    èģĶæĴŃ
    -0.06
    POSITIVE LOGITS
    计æıIJ
    0.10
     pessim
    0.10
     losses
    0.09
    åĩıåĢ¼
    0.08
    prob
    0.08
    æįŁå¤±
    0.08
    æįŁå¤±çļĦ
    0.08
    æĤ²è§Ĥ
    0.08
     loss
    0.08
     recover
    0.08
    Activations Density 0.004%

    No Known Activations