© 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. 37639
    Prev
    Next
    INDEX
    Explanations

    aspect importance

    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
     developmental
    -0.07
    azan
    -0.07
    raten
    -0.06
    åĮĹè¾°
    -0.06
     Purdue
    -0.06
    .rot
    -0.06
    ajah
    -0.06
    æŀľçĦ¶æĺ¯
    -0.06
    uat
    -0.06
    è¬
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģåıĬæŶ
    0.08
    oreach
    0.07
    çŁ¥éģĵä»ĸ
    0.07
     naquele
    0.07
    ×Ļר×ķ
    0.07
    ä¸įç»ıæĦı
    0.07
    æīįçŁ¥éģĵ
    0.07
    _exclude
    0.07
    æĺ¯å½ĵåīį
    0.07
    eker
    0.07
    Activations Density 0.005%

    No Known Activations