© 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. 24054
    Prev
    Next
    INDEX
    Explanations

    business and organizational functions

    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
    amo
    -0.08
    esa
    -0.07
    为ä¹ĭ
    -0.07
    esas
    -0.07
    (?
    -0.07
    èī³éĺ³
    -0.07
    Õ¡Õ¿
    -0.07
     Forbes
    -0.07
    bek
    -0.07
    ogl
    -0.06
    POSITIVE LOGITS
    juh
    0.07
    å¦Ĥæľīä¾µæĿĥ
    0.07
     gig
    0.07
    ä¹±çļĦ
    0.07
    ä¸Ģå¤ķ
    0.06
    åĴĮæĻºæħ§
    0.06
    ãģ¨ãģĭ
    0.06
    éŨä¸ĭ
    0.06
     noqa
    0.06
    _CSR
    0.06
    Activations Density 0.122%

    No Known Activations