© 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. 52047
    Prev
    Next
    INDEX
    Explanations

    cost, fee, or limit

    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
    æĸĽ
    -0.08
    æĿ¥è¶Ĭ
    -0.08
    IFY
    -0.08
    enco
    -0.08
    éĻµåİ¿
    -0.08
     Pelosi
    -0.08
     Sinopsis
    -0.08
    ilos
    -0.08
    å®Ļ
    -0.08
    Ñħоз
    -0.07
    POSITIVE LOGITS
     (~
    0.16
    æłĩåĩĨ为
    0.12
    约为
    0.12
    ä¸ĢèĪ¬ä¸º
    0.12
    éĢļ常为
    0.11
    é«ĺè¾¾
    0.11
     ($
    0.09
    (~
    0.09
    é»ĺ
    0.09
    å®ļ为
    0.09
    Activations Density 0.125%

    No Known Activations