© 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. 56056
    Prev
    Next
    INDEX
    Explanations

    example code structure

    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
    بØŃ
    -0.07
    继
    -0.07
    Rel
    -0.07
     rel
    -0.07
     Rel
    -0.06
    rel
    -0.06
    infeld
    -0.06
    åijľåijľ
    -0.06
    è¿Ļé¢Ĺ
    -0.06
     ÙĦØ·
    -0.06
    POSITIVE LOGITS
    EXAMPLE
    0.08
    ä¾ĭåŃIJ
    0.08
    åĩĮéľĦ
    0.07
    umi
    0.07
    igd
    0.07
    etan
    0.07
    çļĦä¾ĭåŃIJ
    0.07
    _inline
    0.07
    ekom
    0.07
    kong
    0.07
    Activations Density 0.035%

    No Known Activations