© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17080
    Prev
    Next
    INDEX
    Explanations

    horizontal rule or divider

    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
     résol
    -0.07
    ulaire
    -0.07
    мп
    -0.07
    .gov
    -0.07
    æīĭæľºå®¢æĪ·ç«¯
    -0.07
    ISM
    -0.07
    eer
    -0.07
    没æľī被
    -0.07
    èµı
    -0.06
     vard
    -0.06
    POSITIVE LOGITS
     dividing
    0.08
    åĪĨéļĶ
    0.08
    åĪĨåī²
    0.08
    线
    0.08
    _separator
    0.08
     ngang
    0.08
    divider
    0.07
     Tren
    0.07
    线çļĦ
    0.07
    éĹ´éļĶ
    0.07
    Activations Density 0.053%

    No Known Activations