© 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. 14095
    Prev
    Next
    INDEX
    Explanations

    document image files

    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
    emun
    -0.08
    elj
    -0.07
    моÑĤ
    -0.07
     padat
    -0.07
    家æľī
    -0.07
    æľīèĩ´
    -0.07
    Ram
    -0.07
     Ramsey
    -0.07
    æŃ»ä¸į
    -0.07
    è§Ĥä¼ĹçļĦ
    -0.07
    POSITIVE LOGITS
    åĪĨå·¦åı³
    0.07
    olvers
    0.07
    ptr
    0.07
     Sorte
    0.06
    lef
    0.06
     hon
    0.06
    າàºĻ
    0.06
    á»ijt
    0.06
    æĹı
    0.06
     Serg
    0.06
    Activations Density 0.001%

    No Known Activations