© 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. 44770
    Prev
    Next
    INDEX
    Explanations

    major incident, polarize, weapons, primera vez

    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
    ç¨
    -0.07
     gener
    -0.07
    çī¹åĭĴ
    -0.07
    óc
    -0.07
    欧
    -0.07
    kota
    -0.06
    -symbol
    -0.06
    设计åıĬ
    -0.06
    éŃħ
    -0.06
    é¡¹çĽ®åıĬ
    -0.06
    POSITIVE LOGITS
    retty
    0.07
    irlines
    0.07
    æĹ¢æĺ¯
    0.07
    æ¯Ķè¾ĥç®Ģåįķ
    0.07
    ä¹İåħ¶
    0.07
    è¿Ľä¸ĢæŃ¥
    0.06
    aju
    0.06
    ÏĢη
    0.06
    修饰
    0.06
    duced
    0.06
    Activations Density 0.007%

    No Known Activations