© 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. 21003
    Prev
    Next
    INDEX
    Explanations

    often indicates or happens

    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
    ation
    -0.07
    ä¸įåĪ©
    -0.07
    atorial
    -0.06
    Expect
    -0.06
    ettle
    -0.06
    æ½ĩ
    -0.06
    æľŁæľĽ
    -0.06
     optim
    -0.06
     Opt
    -0.05
    åİ»
    -0.05
    POSITIVE LOGITS
    enda
    0.09
    utow
    0.08
    交éģĵ
    0.08
    nak
    0.08
    ÙİÙijا
    0.08
    onya
    0.08
    zen
    0.08
    Ãło
    0.08
    éĢĨåıĺ
    0.08
    okal
    0.08
    Activations Density 0.128%

    No Known Activations