© 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. 48153
    Prev
    Next
    INDEX
    Explanations

    latex

    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
    ych
    -0.07
    æŃ»ä¸į
    -0.07
    деб
    -0.07
    .Atomic
    -0.06
    imson
    -0.06
    çļĦæĸ¹åIJij
    -0.06
    çĥĪçģ«
    -0.06
    entially
    -0.06
    çļĦåıijçĶŁ
    -0.06
    è¿ľèĪª
    -0.06
    POSITIVE LOGITS
    inois
    0.08
    standing
    0.07
    æµģåĬ¨çļĦ
    0.07
    ifte
    0.07
     Decompiled
    0.07
    ẩm
    0.07
    Ñĩик
    0.07
    etzung
    0.06
    oggio
    0.06
    ITU
    0.06
    Activations Density 0.004%

    No Known Activations