© 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. 10126
    Prev
    Next
    INDEX
    Explanations

    printf format specifiers

    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
    kao
    -0.07
    åIJĽå®ī
    -0.07
    elaar
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.06
    çļĦãģ«
    -0.06
    ammel
    -0.06
     Cle
    -0.06
    夾
    -0.06
    's
    -0.06
     اجتÙħاع
    -0.05
    POSITIVE LOGITS
    trinsic
    0.08
    åı¥è¯Ŀ说
    0.08
    ago
    0.07
    oseb
    0.07
     parch
    0.07
    irty
    0.07
    åħ°è¾¾
    0.07
     reemb
    0.07
    æĪijå°±è¦ģ
    0.07
    estring
    0.07
    Activations Density 0.022%

    No Known Activations