© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61571
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
     Topl
    -0.07
    iewicz
    -0.07
     hoÃłi
    -0.07
    大æĦı
    -0.07
    çļĦ人çĶŁ
    -0.07
    .cgi
    -0.07
    æŀī
    -0.07
     &_
    -0.07
    以身
    -0.07
    æĻļéĹ´
    -0.07
    POSITIVE LOGITS
    inii
    0.06
    å¤§åľ°éľĩ
    0.06
    ValuePair
    0.06
    使åĩº
    0.06
    anjang
    0.06
    åĶ
    0.06
    æĮª
    0.06
    ocache
    0.06
    mdb
    0.06
    åķ¬
    0.06
    Activations Density 0.001%

    No Known Activations