© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code delimiters

    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
    è¿ĺåı¯ä»¥éĢļè¿ĩ
    -0.07
    轻质
    -0.07
    è¿ĺèĥ½
    -0.07
    è¿ĺåŃĺåľ¨
    -0.07
     through
    -0.07
    èĥĮè´Ł
    -0.06
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    -0.06
    alap
    -0.06
    åĩºå¤´
    -0.06
    è¿ĺåı¯èĥ½
    -0.06
    POSITIVE LOGITS
    isie
    0.09
    urul
    0.08
    zey
    0.08
     вед
    0.07
    éļ¶å±ŀ
    0.07
    urale
    0.07
    auge
    0.07
    icode
    0.07
    ienz
    0.07
    achie
    0.07
    Activations Density 0.079%

    No Known Activations