© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17089
    Prev
    Next
    INDEX
    Explanations

    BEGIN or start

    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
    åĪ©
    -0.08
    æ¯Ľ
    -0.07
     maté
    -0.07
    ä¸įèĻļ
    -0.06
    Welcome
    -0.06
    uku
    -0.06
    说
    -0.06
    ãĥĶãĥ³ãĤ°
    -0.06
     welcome
    -0.06
    è¿ŀçݯ
    -0.06
    POSITIVE LOGITS
    engl
    0.07
    çĮĽçļĦ
    0.07
    å·´åĭĴ
    0.07
    eves
    0.07
    åİŁå®ļ
    0.07
    errer
    0.07
    çĮĽåľ°
    0.07
    æŃ£åĽłä¸º
    0.07
     izman
    0.07
     ethic
    0.07
    Activations Density 0.004%

    No Known Activations