© 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. 40760
    Prev
    Next
    INDEX
    Explanations

    control, manipulate, stimulate, test

    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
    ajah
    -0.09
     isize
    -0.08
    lazy
    -0.08
    Ïģη
    -0.08
    è¸Ĭ
    -0.08
    æĶ¾å¼ĥäºĨ
    -0.07
    erken
    -0.07
    å·¥ä½ľæķĪçİĩ
    -0.07
    ä¸īçݯ
    -0.07
    ClassName
    -0.07
    POSITIVE LOGITS
     test
    0.12
     tester
    0.12
    æµĭè¯ķ
    0.12
     Test
    0.11
    è¿Ľè¡Įæµĭè¯ķ
    0.10
    -test
    0.10
    被æµĭ
    0.10
     controlled
    0.10
     testing
    0.10
     иÑģпÑĭ
    0.10
    Activations Density 0.490%

    No Known Activations