© 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. 14697
    Prev
    Next
    INDEX
    Explanations

    size in KB or bytes

    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
    ayi
    -0.07
    横
    -0.07
    ÐĴÐĺ
    -0.06
    æĶ¾å®½
    -0.06
    æ£ļ
    -0.06
    [
    -0.06
    urry
    -0.06
    artner
    -0.06
    ÙĦÙĩ
    -0.06
    &utm
    -0.06
    POSITIVE LOGITS
    byte
    0.10
    Byte
    0.10
     fileSize
    0.09
    æĸĩ件大å°ı
    0.09
    -byte
    0.09
     filesize
    0.09
    大å°ı
    0.09
    大å°ı为
    0.09
     byte
    0.09
     file
    0.08
    Activations Density 0.053%

    No Known Activations