© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17106
    Prev
    Next
    INDEX
    Explanations

    ( followed by from

    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
    è¿Ļä¹Ī好çļĦ
    -0.08
    SWG
    -0.08
    vvm
    -0.08
    ä¹ĭæīį
    -0.08
    翼翼
    -0.07
    รู
    -0.07
    并æī¿æĭħ
    -0.07
    cede
    -0.07
    è¿Ļæł·å°±åı¯ä»¥
    -0.07
    ERM
    -0.07
    POSITIVE LOGITS
    çļĦ建ç«ĭ
    0.07
    åħ¶ä»ĸçļĦ
    0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.07
     lainnya
    0.07
    以åıĬåħ¶ä»ĸ
    0.07
    åħ¶å®ĥ
    0.06
    åŁŁ
    0.06
    ryo
    0.06
    agni
    0.06
    voi
    0.06
    Activations Density 1.237%

    No Known Activations