© 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. 19935
    Prev
    Next
    INDEX
    Explanations

    help, prove, eliminate, resistant

    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
     probably
    -0.13
     presumably
    -0.13
     usually
    -0.12
     basically
    -0.12
    probably
    -0.11
    å¾Īåı¯èĥ½
    -0.11
     likely
    -0.11
     essentially
    -0.10
    likely
    -0.10
    å¾Ģå¾Ģ
    -0.10
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.14
     depending
    0.14
     dependendo
    0.12
    æĸĩ件æĪĸ
    0.11
     someday
    0.11
    æĢ§æĪĸ
    0.11
    depending
    0.11
    æĬķèµĦæĪĸ
    0.11
    人æĪĸ
    0.11
    åĽ¾çīĩæĪĸ
    0.11
    Activations Density 0.610%

    No Known Activations