© 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. 47377
    Prev
    Next
    INDEX
    Explanations

    simple example or setup

    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
    /errors
    -0.06
     lu
    -0.06
    æ²¾
    -0.06
    ussy
    -0.06
    concat
    -0.06
    çŃ
    -0.06
    mane
    -0.06
    æĩ
    -0.06
    èį
    -0.06
    Formatter
    -0.06
    POSITIVE LOGITS
    ä¾ĭåŃIJ
    0.11
    èĻļæŀĦ
    0.11
     Simple
    0.10
    å¾Īç®Ģåįķ
    0.10
    为ä¾ĭ
    0.10
    示ä¾ĭ
    0.10
    simple
    0.10
    ç®ĢåįķçļĦ
    0.10
     simple
    0.10
     simplistic
    0.10
    Activations Density 0.068%

    No Known Activations