© 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. 22479
    Prev
    Next
    INDEX
    Explanations

    securely, appropriately, adequately, properly

    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
     ÑıкобÑĭ
    -0.08
    æľīçĤ¹åĥı
    -0.07
     simply
    -0.07
    ä¿Ĺ称
    -0.07
    pjes
    -0.07
    éģŃåĪ°äºĨ
    -0.07
     basically
    -0.06
     unknow
    -0.06
    æī¾æĿ¥
    -0.06
    raquo
    -0.06
    POSITIVE LOGITS
     adequately
    0.12
     appropriately
    0.11
     securely
    0.11
     appropriate
    0.11
    ä½Ĩèĩ³å°ij
    0.10
    æľīè¶³å¤ŁçļĦ
    0.10
     clearly
    0.10
    èĩ³å°ij
    0.10
     properly
    0.10
     adequate
    0.10
    Activations Density 0.047%

    No Known Activations