© 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. 25580
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms

    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
    åĪĨè¡Į
    -0.07
     tricks
    -0.07
     clever
    -0.07
    éĤ£è¾¹çļĦ
    -0.07
    DTD
    -0.07
    é£ŀç¿Ķ
    -0.07
     gadget
    -0.07
    åĪ
    -0.07
    ispens
    -0.07
     gadgets
    -0.07
    POSITIVE LOGITS
     pursuant
    0.10
     presently
    0.09
     currently
    0.09
     utilizing
    0.09
     entirety
    0.09
     annually
    0.08
     historic
    0.08
     herein
    0.08
    util
    0.08
    currently
    0.08
    Activations Density 0.908%

    No Known Activations