© 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. 60470
    Prev
    Next
    INDEX
    Explanations

    gestational age and weight

    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
    orios
    -0.09
     ÙĨد
    -0.08
    kees
    -0.08
    æ¸ħæ²³
    -0.08
    cim
    -0.08
    è½ī
    -0.08
    tees
    -0.08
    wäl
    -0.08
    elop
    -0.08
    intis
    -0.07
    POSITIVE LOGITS
    æĹłè®ºæĺ¯
    0.10
    ±
    0.08
    ä¸į论æĺ¯
    0.08
    ä¸į管æĺ¯
    0.08
    æĹłè®º
    0.08
    çĦ¡è«ĸæĺ¯
    0.07
    èĮħ
    0.07
    æĹłè®ºä»İ
    0.07
     ±
    0.07
    èĢĮä¸Ķæĺ¯
    0.07
    Activations Density 0.044%

    No Known Activations