© 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. 31529
    Prev
    Next
    INDEX
    Explanations

    tech companies and abbreviations

    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
    avra
    -0.08
     PROB
    -0.08
    å·²åľ¨
    -0.08
    èvre
    -0.08
    enin
    -0.07
    æľ¬æĸĩ为
    -0.07
    æĦļ
    -0.07
    resa
    -0.07
    otto
    -0.07
    remen
    -0.07
    POSITIVE LOGITS
    带
    0.09
    amay
    0.07
    ëł
    0.06
    缴æİ¥è¿Ľåħ¥
    0.06
    zá
    0.06
    ataka
    0.06
    ÙĨاÙĩا
    0.06
    á»įng
    0.06
    åıªèĥ½
    0.06
    alt
    0.06
    Activations Density 0.047%

    No Known Activations