© 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. 44957
    Prev
    Next
    INDEX
    Explanations

    assume, value, contradiction, intersection, background

    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
    å¾Ĺ人
    -0.08
    æĺĩ
    -0.07
    礼
    -0.07
    èĽ
    -0.07
    awa
    -0.06
    ABIL
    -0.06
    人æĦı
    -0.06
    iden
    -0.06
    å°Ĭ
    -0.06
    hon
    -0.06
    POSITIVE LOGITS
    å¦ĤæŀľçľŁçļĦ
    0.08
     Would
    0.08
    would
    0.08
    æİ¨è¿Ľä¼ļ
    0.08
    åģĩ设
    0.08
    åģĩ
    0.08
    å¼ķ以为
    0.08
     would
    0.08
    ä¼ļ导èĩ´
    0.08
    Would
    0.07
    Activations Density 0.009%

    No Known Activations