© 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. 64253
    Prev
    Next
    INDEX
    Explanations

    onto or on top

    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
    å½Ĵå±ŀ
    -0.07
     constituent
    -0.07
    å¿Ĺ
    -0.07
    amental
    -0.06
    encil
    -0.06
    éĻ¶åĨ¶
    -0.06
    åĪĹåħ¥
    -0.06
     isol
    -0.06
    æ¡ĥæĿİ
    -0.06
    erable
    -0.06
    POSITIVE LOGITS
     groÃŁzüg
    0.10
    è¦ĨçĽĸçİĩ
    0.09
    ä¸Ĭä¸Ģå±Ĥ
    0.09
    coverage
    0.09
     coverage
    0.08
    åĿĩåĮĢ
    0.08
     onto
    0.08
     generous
    0.08
    pong
    0.08
     generously
    0.08
    Activations Density 0.034%

    No Known Activations