© 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. 55661
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
    elib
    -0.07
     \"{
    -0.07
    verted
    -0.07
    éºĵ
    -0.07
    lland
    -0.07
    зо
    -0.07
    ioned
    -0.06
    ìľł
    -0.06
    æĿİä¸ĸ
    -0.06
    aload
    -0.06
    POSITIVE LOGITS
    è¿Ļ个è¯į
    0.10
     typically
    0.07
    onne
    0.07
    ä¹īè¯į
    0.07
    leigh
    0.07
    æķħåIJį
    0.07
    åıĪ称
    0.07
    èݹ
    0.06
    agal
    0.06
    itt
    0.06
    Activations Density 0.357%

    No Known Activations