© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29842
    Prev
    Next
    INDEX
    Explanations

    language metadata or special characters

    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
    ega
    -0.07
    eger
    -0.07
    æĢ»ä¸įèĥ½
    -0.06
    åIJ¦åĪĻ
    -0.06
    egy
    -0.06
    zion
    -0.06
     }}}
    -0.06
    Otherwise
    -0.06
    hort
    -0.06
    ORIZ
    -0.06
    POSITIVE LOGITS
    åĴĮåIJĮäºĭ
    0.08
    accio
    0.08
    ooke
    0.07
     Raven
    0.07
    aru
    0.07
    ä¸ŃåIJ«
    0.06
    gli
    0.06
    Unnamed
    0.06
    elang
    0.06
    âĺĨâĺĨ
    0.06
    Activations Density 0.001%

    No Known Activations