© 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. 49055
    Prev
    Next
    INDEX
    Explanations

    lists and headings

    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
    aire
    -0.07
    åĪĽä¸ĭ
    -0.06
    iel
    -0.06
    uler
    -0.06
    æľĿ
    -0.06
    æĬĢæľ¯ä¸Ĭ
    -0.06
    iology
    -0.06
    ies
    -0.06
    绣
    -0.06
     inc
    -0.06
    POSITIVE LOGITS
    ç»ĵè¯Ń
    0.12
    ç»ĵæĿŁè¯Ń
    0.10
    æľĢæĸ°æĸĩç«ł
    0.09
    æľ¬åĽŀçŃĶ
    0.09
    tright
    0.09
    ãģĿãģ®ä»ĸ
    0.09
    举个
    0.09
     Conclusion
    0.08
    管çIJĨåıĬ
    0.08
    tru
    0.08
    Activations Density 0.025%

    No Known Activations