© 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. 7482
    Prev
    Next
    INDEX
    Explanations

    seeking confirmation or understanding

    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
    .collections
    -0.08
    _IT
    -0.08
    hiri
    -0.08
    alz
    -0.08
    å±ħçĦ¶æĺ¯
    -0.08
    çļĦç¥Ŀç¦ı
    -0.08
    доÑĢ
    -0.07
    Ñħе
    -0.07
    Released
    -0.07
    个åĽŀçŃĶ
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦æŃ£ç¡®
    0.09
    tent
    0.08
     correct
    0.07
    æ²¼
    0.07
    æĺ¯æŃ£ç¡®çļĦ
    0.07
    æĭīæī¯
    0.07
     Ting
    0.07
     tent
    0.07
    祺
    0.07
    ApplicationBuilder
    0.06
    Activations Density 0.338%

    No Known Activations