© 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. 44652
    Prev
    Next
    INDEX
    Explanations

    nature, thunder, pressure, competition, blocks, backup, monsters

    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
     which
    -0.09
    à¸Ĺีà¹Īà¸Īะ
    -0.07
     اÛĮÙĨÚ©Ùĩ
    -0.07
    ãģĮãģĵãģ®
    -0.07
    è¿Ļæĺ¯ä¸Ģ个
    -0.07
     اÙĦتÙĬ
    -0.07
     olyan
    -0.07
     tehát
    -0.06
    èĢĮè¦ģ
    -0.06
    åĽłä¸ºè¿Ļ个
    -0.06
    POSITIVE LOGITS
     appunto
    0.16
    çļĦä¸ĢåĪĩéĥ½
    0.10
     justement
    0.09
     magari
    0.09
    <|box_end|>
    0.09
    alsy
    0.09
    ãģĭãģ¤
    0.08
    ipay
    0.08
    quiera
    0.08
    尤为
    0.08
    Activations Density 0.386%

    No Known Activations