© 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. 26837
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts

    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
    вани
    -0.08
    çī¹æľī
    -0.07
    ptico
    -0.07
    /from
    -0.07
    æĺ¯è°ģ
    -0.07
    iken
    -0.07
    cape
    -0.07
    edan
    -0.07
    -0.07
    }}{{
    -0.07
    POSITIVE LOGITS
    å±ĤéĿ¢ä¸Ĭ
    0.10
    -wise
    0.10
     abound
    0.10
     occurs
    0.10
    ÙĮ
    0.09
     wise
    0.08
    ä¹Łç½¢
    0.08
    åľ¨è¿ĻéĩĮ
    0.08
    åĪ°è¿ĻéĩĮ
    0.08
    ä»İè¿ĻéĩĮ
    0.08
    Activations Density 0.674%

    No Known Activations