© 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. 27148
    Prev
    Next
    INDEX
    Explanations

    real-time information and analysis

    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
    isFunction
    -0.07
    mals
    -0.07
    æ·±æĢĿ
    -0.07
    éĩįéĩį
    -0.07
    éķ¿æľŁä½¿çĶ¨
    -0.07
    land
    -0.07
    黯çĦ¶
    -0.07
    åĸĦèī¯çļĦ
    -0.07
    æĺ¯ä¸º
    -0.07
    eni
    -0.07
    POSITIVE LOGITS
    å®ŀæŶ
    0.13
    à¸Ĺัà¸Ļ
    0.11
    /live
    0.10
    aneously
    0.10
    åĬ¨æĢģ
    0.09
    (real
    0.09
    åį³æŶ
    0.09
    (dynamic
    0.09
     live
    0.09
    live
    0.08
    Activations Density 0.092%

    No Known Activations