© 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. 33419
    Prev
    Next
    INDEX
    Explanations

    sorting lists

    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
    çĮ
    -0.07
    ÐĵС
    -0.07
    æĿ¥å¾Ĺ
    -0.07
    cre
    -0.06
    ç«ĭ
    -0.06
    ots
    -0.06
    åĪ¶ä½ľäºº
    -0.06
    illin
    -0.06
    rett
    -0.06
     ell
    -0.06
    POSITIVE LOGITS
    ä¸Ģéĥİ
    0.09
    @(
    0.08
     followed
    0.08
    ìĸ´ëĵľ
    0.08
    ãĤĵãģ°ãĤĵ
    0.07
    HeaderView
    0.07
    à¤ķà¥įरम
    0.07
    upert
    0.07
    CAF
    0.07
     conte
    0.07
    Activations Density 0.010%

    No Known Activations