© 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. 60944
    Prev
    Next
    INDEX
    Explanations

    computing and estimation

    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
    ¯
    -0.07
    åİŁåīĩ
    -0.07
    à¸ģาย
    -0.07
    好äºĭ
    -0.07
    åİŁæĿ¥çļĦ
    -0.07
    åİŁæľīçļĦ
    -0.06
     Ñģобой
    -0.06
     Ñģб
    -0.06
    åī
    -0.06
    æĴ¤
    -0.06
    POSITIVE LOGITS
     accurate
    0.10
     elusive
    0.09
     coveted
    0.08
    æīĢéľĢ
    0.08
    ERIC
    0.08
    è¦ģçŁ¥éģĵ
    0.08
    /find
    0.08
     coefficients
    0.08
    涯
    0.08
     estimates
    0.07
    Activations Density 0.249%

    No Known Activations