© 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. 7703
    Prev
    Next
    INDEX
    Explanations

    fetal development stages

    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
    มวลà¸Ĭà¸Ļ
    -0.08
    ýt
    -0.08
    üss
    -0.08
     nhau
    -0.07
    evity
    -0.07
    vim
    -0.07
    fully
    -0.07
    yer
    -0.07
    mien
    -0.07
    ypse
    -0.07
    POSITIVE LOGITS
    段éļİ
    0.11
    æľŁåĴĮ
    0.10
    æľŁçļĦ
    0.10
    æľŁ
    0.10
    hood
    0.09
    éĺ¶æ®µçļĦ
    0.09
    éĺ¶æ®µ
    0.09
    æľŁãģ®
    0.08
    -stage
    0.08
    åĴĮå¦Īå¦Ī
    0.08
    Activations Density 0.106%

    No Known Activations