© 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. 4730
    Prev
    Next
    INDEX
    Explanations

    consumer bureau

    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
     ...\
    -0.08
    åĨĩ
    -0.08
     immoral
    -0.07
    å¸ĮæľĽå¯¹æĤ¨
    -0.07
     ...)
    -0.07
     Zij
    -0.07
    ircular
    -0.07
    éĩ
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    éĤ£è¾¹
    -0.07
    POSITIVE LOGITS
    çĭĦ
    0.07
     ("
    0.07
    çĮĽåľ°
    0.07
    æħĪ
    0.06
     understandably
    0.06
     "
    0.06
     "**
    0.06
    è¨Ģ
    0.06
    (!
    0.06
    æ¯ıæ¯ı
    0.06
    Activations Density 0.001%

    No Known Activations