© 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. 25299
    Prev
    Next
    INDEX
    Explanations

    starting or reverse

    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
    zor
    -0.07
    å¿Ĺ强
    -0.07
    天涯
    -0.06
    éĻĮ
    -0.06
    ãģ¤ãģı
    -0.06
    ä¸ŃåįĹ
    -0.06
    sv
    -0.06
    ç´ł
    -0.06
    é½
    -0.06
    ç«ĭä½ĵ
    -0.06
    POSITIVE LOGITS
    éĢĨè¡Į
    0.12
     reverse
    0.12
    .reverse
    0.12
    éĢĨåIJij
    0.12
    Reverse
    0.11
     backward
    0.11
    åıįåIJij
    0.11
    reverse
    0.11
     Reverse
    0.11
    åĢĴ
    0.11
    Activations Density 0.045%

    No Known Activations