© 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. 52030
    Prev
    Next
    INDEX
    Explanations

    under conditions

    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
    enfant
    -0.07
    ìłĦ문
    -0.07
    ToOne
    -0.07
    æīį对
    -0.06
     Thom
    -0.06
    echos
    -0.06
    ikin
    -0.06
     capt
    -0.06
    å½ĵåŃ©åŃIJ
    -0.06
    ä»»ä½ķ人
    -0.06
    POSITIVE LOGITS
     donc
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.08
     therefore
    0.08
    colari
    0.08
    åĽłæѤ
    0.08
     appunto
    0.08
    çļĦè¿Ļ个
    0.08
     wiÄĻc
    0.07
    uges
    0.07
    ãģ§ãģĻãģĭãĤī
    0.07
    Activations Density 0.207%

    No Known Activations