© 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. 57962
    Prev
    Next
    INDEX
    Explanations

    prepare for

    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
    -0.08
    ywa
    -0.07
    plorer
    -0.07
    .websocket
    -0.07
    ometown
    -0.07
    inggu
    -0.07
    ástico
    -0.07
    oops
    -0.07
    ëŀĺ
    -0.07
    à¹Īà¸Ļ
    -0.07
    POSITIVE LOGITS
    就绪
    0.15
    è¿İæİ¥
    0.13
    åĩĨå¤ĩ
    0.11
     sẵn
    0.10
    åĩĨå¤ĩçļĦ
    0.10
     inför
    0.09
    ares
    0.09
    åĩĨå¤ĩ好
    0.09
    æºĸåĤĻ
    0.09
    åħħåĪĨçļĦ
    0.09
    Activations Density 0.073%

    No Known Activations