© 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. 17419
    Prev
    Next
    INDEX
    Explanations

    album

    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
     Postagem
    -0.11
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.10
     acresc
    -0.10
    orable
    -0.10
     trám
    -0.09
    owników
    -0.09
     Postado
    -0.09
    åįĥæĸ¹
    -0.09
     esclar
    -0.09
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼
    -0.09
    POSITIVE LOGITS
     de
    0.07
     P
    0.07
    i
    0.07
     The
    0.06
    0.06
     Bö
    0.06
     i
    0.06
     "
    0.06
    ats
    0.06
     V
    0.06
    Activations Density 2.049%

    No Known Activations