© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    instructions, rules, choice, poll

    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
    èĤłèĥĥ
    -0.08
    æµģåĬ¨
    -0.07
    äºĶéĩij
    -0.07
    èĩ³é«ĺ
    -0.07
    pite
    -0.07
    æµģåĬ¨çļĦ
    -0.07
    æį¡èµ·
    -0.07
    åĽłä¸ºä½ł
    -0.07
    assis
    -0.07
    ä¹ŁåºĶ该
    -0.07
    POSITIVE LOGITS
    ä¸ĢéĹ®
    0.07
    inkel
    0.07
     format
    0.07
    Choices
    0.07
     question
    0.07
    æıIJ示
    0.07
     questions
    0.07
    åıĤåĬłéĿ¢è¯ķ
    0.06
    ansom
    0.06
     ìłľìĭľ
    0.06
    Activations Density 0.001%

    No Known Activations