© 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. 33771
    Prev
    Next
    INDEX
    Explanations

    form and notation

    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
    è¹´
    -0.07
     Rov
    -0.06
    uruh
    -0.06
    brigen
    -0.06
    stat
    -0.06
    å¾Ģ
    -0.06
     kap
    -0.06
    ÏĥÏĦι
    -0.06
    lada
    -0.06
    reiro
    -0.06
    POSITIVE LOGITS
     format
    0.12
    æł¼å¼ı
    0.11
    å½¢å¼ı
    0.10
     notation
    0.09
    åĨĻæ³ķ
    0.09
    æł¼å¼ıçļĦ
    0.09
    format
    0.09
     Format
    0.09
     form
    0.08
     style
    0.08
    Activations Density 0.061%

    No Known Activations