© 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. 44653
    Prev
    Next
    INDEX
    Explanations

    Granted, sure, true

    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«ŁçĦ¶æĺ¯
    -0.09
    è¶ħè¿ĩ约
    -0.09
    ç«Ł
    -0.08
     Padahal
    -0.08
    ç«Łæĺ¯
    -0.08
    çĻ»å½ķæŁ¥çľĭ
    -0.08
    å±ħçĦ¶æĺ¯
    -0.08
    请åĬł
    -0.08
    åĮªæµħ
    -0.08
    åı¯åIJ¦
    -0.08
    POSITIVE LOGITS
    ãĤĤãģĤãĤĬãģ¾ãģĻãģĮ
    0.09
    —but
    0.08
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.08
    ,but
    0.08
    ê²łì§Ģë§Į
    0.07
    èħĨ
    0.07
    íķĺê²ł
    0.07
    ä½Ĩèĩ³å°ij
    0.07
    ãģĦãģ¾ãģĻãģĮ
    0.07
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    0.07
    Activations Density 0.704%

    No Known Activations