© 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. 29074
    Prev
    Next
    INDEX
    Explanations

    pair

    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
    dess
    -0.07
    PEND
    -0.07
    tap
    -0.07
    avia
    -0.07
    å¼ĢåºŃ
    -0.07
    çİĩåħĪ
    -0.07
    æĩ¿
    -0.07
    åİŁæ±ģ
    -0.06
    nal
    -0.06
     outright
    -0.06
    POSITIVE LOGITS
     pair
    0.19
    Pair
    0.16
     pairs
    0.16
     Pair
    0.15
    _pair
    0.15
    pair
    0.14
    çļĦä¸Ģ对
    0.14
    ä¸Ģ对
    0.14
     pairing
    0.14
    .pair
    0.13
    Activations Density 0.130%

    No Known Activations