© 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. 52173
    Prev
    Next
    INDEX
    Explanations

    journaling and publication details

    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
    OGO
    -0.09
    ERV
    -0.09
    ruck
    -0.08
    èµĦ讯ä¸Ńå¿ĥ
    -0.08
     Khang
    -0.08
    ä¸Ģ女
    -0.08
    æľĪä¸Ĭ
    -0.08
    ommer
    -0.08
    缸åħ³èµĦ讯
    -0.08
    umpul
    -0.08
    POSITIVE LOGITS
    0.07
     Advances
    0.06
     âĢİ
    0.06
    â
    0.06
     https
    0.06
     P
    0.06
    ord
    0.06
    âĢĮ
    0.06
    åĪ«
    0.06
    èİ«
    0.06
    Activations Density 0.122%

    No Known Activations