© 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. 63992
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    åŃIJçļĦ
    -0.07
    ület
    -0.07
    abyte
    -0.07
    pawn
    -0.07
    æľīçĤ¹
    -0.07
    lington
    -0.07
    xBC
    -0.07
    lum
    -0.07
    åŃIJ
    -0.07
     excer
    -0.06
    POSITIVE LOGITS
    ëĮĵ
    0.07
    .Authorization
    0.07
    rig
    0.07
    ä¸Ńå¿ĥçŃī
    0.07
    ä½Ĩ没æľī
    0.07
     nargs
    0.07
    rax
    0.06
    éĵ®
    0.06
    建ç«ĭä¸Ģ个
    0.06
    èĬ³åįİ
    0.06
    Activations Density 0.044%

    No Known Activations