© 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. 55791
    Prev
    Next
    INDEX
    Explanations

    combining information or concepts

    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
    é¼İé¼İ
    -0.08
    xies
    -0.07
    åĬĽè¡Į
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    ewidth
    -0.07
    niec
    -0.06
    eca
    -0.06
    å¿ĥå¿ĥ
    -0.06
    aduras
    -0.06
    ype
    -0.06
    POSITIVE LOGITS
    æķ´åIJĪ
    0.10
     disparate
    0.10
    èIJĥ
    0.09
    åľ¨ä¸Ģèµ·
    0.09
    æ¦Ĥæĭ¬
    0.09
    รวม
    0.09
     combining
    0.09
    å½Ĵ纳
    0.09
     integrating
    0.09
    æĭ¢
    0.09
    Activations Density 0.044%

    No Known Activations