© 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. 20450
    Prev
    Next
    INDEX
    Explanations

    transformations, Lorentz, activity, bases

    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
    uket
    -0.08
    anth
    -0.08
     Madura
    -0.07
    -animation
    -0.07
    ONS
    -0.07
    ather
    -0.07
    cko
    -0.07
    æĮĩäºĨæĮĩ
    -0.07
    ä¸īåĨľ
    -0.07
    æĻļ
    -0.07
    POSITIVE LOGITS
    åĪ°åľº
    0.07
    åıĺæį¢
    0.07
    erez
    0.07
    éĤ£éĩĮçļĦ
    0.07
    brig
    0.07
     blinded
    0.07
    æĹłèĥ½
    0.07
     Bereits
    0.07
    è¿IJ
    0.07
    转æį¢
    0.07
    Activations Density 0.004%

    No Known Activations