© 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. 4594
    Prev
    Next
    INDEX
    Explanations

    end of clauses or phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĶļèĩ³æĺ¯
    -0.08
    ä¹ĥèĩ³
    -0.08
     whenever
    -0.08
    —that
    -0.07
    å°½åı¯èĥ½åľ°
    -0.07
    —which
    -0.07
    åıªæľīè¿Ļæł·
    -0.07
    —as
    -0.06
    æł¹æľ¬å°±æ²¡æľī
    -0.06
    以便äºİ
    -0.06
    POSITIVE LOGITS
     Tôn
    0.08
     joten
    0.08
    ä¸Ĭè¿°ä½ľåĵģ
    0.07
     wiÄĻc
    0.07
    agher
    0.07
    appelle
    0.07
     donc
    0.07
     kiá»ĩn
    0.07
    ignet
    0.07
    ä¸Ģé«Ķ
    0.07
    Activations Density 0.016%

    No Known Activations