© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22812
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
    anel
    -0.09
    åı¯ä»¥éģ¿åħį
    -0.07
    bery
    -0.07
    羿
    -0.07
     grew
    -0.07
    สาà¸Ļ
    -0.07
    ietf
    -0.07
    éķ¿å¤§
    -0.07
    éģ¿åħįäºĨ
    -0.07
    .removeEventListener
    -0.07
    POSITIVE LOGITS
     usk
    0.09
    åıªæľīä¸Ģ个
    0.08
    ilah
    0.08
    夷
    0.08
    ä»ĸåıª
    0.08
     einzig
    0.08
     Us
    0.08
    åIJİèħ¿
    0.07
    efeld
    0.07
    ALAR
    0.07
    Activations Density 0.048%

    No Known Activations