© 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. 24852
    Prev
    Next
    INDEX
    Explanations

    still, not, improve, better

    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
    _AA
    -0.07
    exe
    -0.07
    å·²æĪIJ
    -0.06
    ä¸įéľĢ
    -0.06
    æĽ
    -0.06
    ETY
    -0.06
     Arb
    -0.06
    ouc
    -0.06
    CI
    -0.06
    ä¸įèĥľ
    -0.06
    POSITIVE LOGITS
    ä»įæľª
    0.16
    è¿ĺæĺ¯æ²¡æľī
    0.14
     still
    0.14
     tampoco
    0.13
    still
    0.13
     STILL
    0.12
     Still
    0.12
    Still
    0.12
    ä»įæŧ
    0.11
    ä¹Łåıªæĺ¯
    0.11
    Activations Density 0.132%

    No Known Activations