© 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. 15208
    Prev
    Next
    INDEX
    Explanations

    shows errors or not correctly

    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
     Atlas
    -0.08
    Atlas
    -0.07
     tzw
    -0.07
    ecat
    -0.07
    çī¹æ®ĬçļĦ
    -0.07
    çĹķ
    -0.07
    ukai
    -0.07
     tzv
    -0.07
    apr
    -0.07
    aper
    -0.07
    POSITIVE LOGITS
     explicitly
    0.08
    æ¡¥éķĩ
    0.08
    æĺİç¡®
    0.08
    ä¸įæıIJ
    0.07
    æĹłè¯¯
    0.07
     correct
    0.07
    æĺİç¡®æĮĩåĩº
    0.07
    æĺİäºĨ
    0.07
    correct
    0.07
     correctly
    0.07
    Activations Density 0.001%

    No Known Activations