© 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. 21498
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    nage
    -0.07
    伦å¤ļ
    -0.07
    òng
    -0.07
    ÙĥÙĬØ©
    -0.07
    urer
    -0.07
    åľ°æľĽçĿĢ
    -0.07
    íĺľ
    -0.07
    haft
    -0.07
    檬
    -0.07
    ikai
    -0.07
    POSITIVE LOGITS
    åħ¸åŀĭçļĦ
    0.07
    à¸Ķุ
    0.06
    otre
    0.06
    apon
    0.06
    ikes
    0.06
     sass
    0.06
    ÑĤип
    0.06
    iani
    0.06
    ÑĢиÑĤ
    0.06
    æ´»äºĨ
    0.06
    Activations Density 0.007%

    No Known Activations