© 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. 22709
    Prev
    Next
    INDEX
    Explanations

    for debugging purposes

    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
     often
    -0.11
    å¾Ģå¾Ģ
    -0.09
     usually
    -0.09
     souvent
    -0.08
     Often
    -0.08
    often
    -0.08
    éĢļ常
    -0.08
     typically
    -0.08
     اغÙĦب
    -0.08
    Often
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.15
    æŁIJ个
    0.13
     somehow
    0.12
    æŁIJ種
    0.11
    æĬķèµĦæĪĸ
    0.10
    æŁIJåĢĭ
    0.10
    éĶĻ误æĪĸ
    0.10
    æĸĩ件æĪĸ
    0.10
    æĢ§æĪĸ
    0.09
     particolari
    0.09
    Activations Density 0.094%

    No Known Activations