© 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. 7185
    Prev
    Next
    INDEX
    Explanations

    helps makes sense

    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
    çļĦä¸Ģå¹´éĩĮ
    -0.09
    æĥ¨
    -0.09
     Kantor
    -0.08
    olos
    -0.07
    è¡
    -0.07
     justru
    -0.07
    ubectl
    -0.07
    >>::
    -0.07
    åı¯æĢķçļĦæĺ¯
    -0.07
    çī¹æĦı
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īæĺ¯
    0.08
    ä»Ģ麼æĺ¯
    0.07
    å°±åı¯ä»¥äºĨ
    0.07
    å¤ŁäºĨ
    0.07
     suffice
    0.07
    å°±ç»ĵæĿŁäºĨ
    0.07
    åıĬéĻĦåĬł
    0.07
    å©·
    0.07
    åŁºæľ¬çļĦ
    0.06
    è¶³å¤ŁäºĨ
    0.06
    Activations Density 0.072%

    No Known Activations