© 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. 33659
    Prev
    Next
    INDEX
    Explanations

    dichotomy, distinguished, separated, divided

    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
    è¹
    -0.08
    æĭŁ
    -0.07
    izzi
    -0.07
    owska
    -0.07
    .module
    -0.07
    åī¯
    -0.06
     оÑĨе
    -0.06
    踪迹
    -0.06
    éĹ»
    -0.06
    æŃ¢
    -0.06
    POSITIVE LOGITS
    åĪĨãģij
    0.09
     separately
    0.08
    ä¸įåIJĮçļĦ
    0.08
     whether
    0.08
    plit
    0.08
     cases
    0.08
     оÑĤделÑĮно
    0.08
     depending
    0.07
    depending
    0.07
     case
    0.07
    Activations Density 0.013%

    No Known Activations