© 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. 44038
    Prev
    Next
    INDEX
    Explanations

    amp; or AA

    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
    /wiki
    -0.08
    sv
    -0.08
    Ñĩо
    -0.07
    دÙĬر
    -0.07
    æ¼Ĩé»ij
    -0.07
    eneg
    -0.07
    arel
    -0.07
    utang
    -0.07
    ç±į
    -0.07
    _general
    -0.07
    POSITIVE LOGITS
     unchanged
    0.11
    ä¾ĿçĦ¶æĺ¯
    0.10
     again
    0.10
    ä»įçĦ¶æĺ¯
    0.10
    æľ¬èº«çļĦ
    0.09
    ä»įçĦ¶åŃĺåľ¨
    0.09
    ä»įçĦ¶
    0.09
    ãģ®ãģ¾ãģ¾
    0.09
     still
    0.09
     itself
    0.09
    Activations Density 0.075%

    No Known Activations