© 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. 46227
    Prev
    Next
    INDEX
    Explanations

    proposed, developed, observed, announced, established, identified, recommended

    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
    奴婢
    -0.08
    åĿIJæľĪåŃIJ
    -0.07
    ovo
    -0.07
    åĩºäºº
    -0.07
    elves
    -0.07
    ilog
    -0.07
    à¸Ĺีà¹Īสำà¸Ħัà¸į
    -0.07
    à¸Ńยà¹Īาà¸ĩà¸Ĺีà¹Ī
    -0.07
    æīĢåıĹ
    -0.07
     ciò
    -0.07
    POSITIVE LOGITS
     earlier
    0.09
     by
    0.08
     during
    0.07
     elsewhere
    0.07
    éré
    0.07
     bợi
    0.07
    ance
    0.06
    /generated
    0.06
    pill
    0.06
     in
    0.06
    Activations Density 0.295%

    No Known Activations