© 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. 58508
    Prev
    Next
    INDEX
    Explanations

    due _on

    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
    ulet
    -0.07
     Seymour
    -0.06
    ierzch
    -0.06
     Flynn
    -0.06
    æķĻä¼ļ
    -0.06
    erate
    -0.06
    ertest
    -0.06
    erb
    -0.06
    ç¾Ķ
    -0.06
    awat
    -0.06
    POSITIVE LOGITS
    èĩªå·±çļĦ梦æĥ³
    0.07
    çĴŁ
    0.07
    illery
    0.06
     swal
    0.06
    cce
    0.06
    æľ¬äººçļĦ
    0.06
    ylum
    0.06
    ium
    0.06
    åIJĦèĩªçļĦ
    0.06
    ìŀī
    0.06
    Activations Density 0.525%

    No Known Activations