© 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. 34670
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
    èį¡èį¡
    -0.07
    å·
    -0.07
    iesta
    -0.07
    åĨįæİ¥
    -0.06
    ifah
    -0.06
    æł·
    -0.06
    ddie
    -0.06
    è°ĥ
    -0.06
     Athe
    -0.06
    inha
    -0.06
    POSITIVE LOGITS
    escu
    0.08
    æĿ¾è½¯
    0.07
    PAL
    0.07
    æĪij社
    0.07
     firstly
    0.07
    ering
    0.06
     ori
    0.06
    byn
    0.06
    ä¾Ŀçħ§
    0.06
    ä¾Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations