© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7062
    Prev
    Next
    INDEX
    Explanations

    general solution formulation

    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
    Negative Logits
    crud
    -0.08
    ÑĤана
    -0.07
    ream
    -0.07
    ordia
    -0.07
    aturi
    -0.07
    ÌĢ
    -0.07
    延
    -0.07
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    emas
    -0.07
    POSITIVE LOGITS
    è¯·çĽ´æİ¥
    0.07
    سط
    0.07
    oire
    0.07
    请填åĨĻ
    0.07
    uter
    0.07
     somehow
    0.07
    太éĥİ
    0.06
    顶å±Ĥ
    0.06
    åıĤèĢĥ
    0.06
    YN
    0.06
    Activations Density 0.093%

    No Known Activations