© 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. 25349
    Prev
    Next
    INDEX
    Explanations

    default settings

    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
    羣æŃ£æĪIJ为
    -0.08
     echt
    -0.07
    羣æŃ£çļĦ
    -0.07
    anga
    -0.07
    羣å®ŀçļĦ
    -0.07
    羣æŃ£å®ŀçİ°
    -0.07
     ideally
    -0.07
    羣å®ŀ
    -0.07
    èĩĤ
    -0.07
    IDE
    -0.07
    POSITIVE LOGITS
    é»ĺ认
    0.24
     default
    0.22
    é»ĺ认çļĦ
    0.21
     Default
    0.20
     defaults
    0.19
    /default
    0.19
    _default
    0.19
    default
    0.19
    Default
    0.19
    é»ĺ
    0.18
    Activations Density 0.182%

    No Known Activations