© 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. 47305
    Prev
    Next
    INDEX
    Explanations

    weekly updates, picks, or daily files

    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
    ç½ij讯
    -0.07
    ç§ī
    -0.06
    éļ¶
    -0.06
    æľ«
    -0.06
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.06
    æīĭ游ç½ij
    -0.06
     Lees
    -0.06
    ä¹Ŀ游
    -0.06
    æľ«æľŁ
    -0.06
    olie
    -0.06
    POSITIVE LOGITS
    allery
    0.08
    ä¼¼æĺ¯
    0.08
    compiled
    0.08
     à¸Ľà¸£à¸°à¸Īำ
    0.08
    utup
    0.08
    ç³»åĪĹ
    0.08
     series
    0.08
    aná
    0.08
    picked
    0.08
     Compiled
    0.08
    Activations Density 0.581%

    No Known Activations