© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9280
    Prev
    Next
    INDEX
    Explanations

    in that spirit of

    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
    è¿Ļæł·å°±åı¯ä»¥
    -0.09
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.08
    éĤ£æł·
    -0.08
    åħ¶ä¸º
    -0.08
    å°±æĺ¯è¿Ļæł·
    -0.08
    ãģĿãģĨãģ§
    -0.08
    å°±æĺ¯è¿Ļä¹Ī
    -0.08
    è¿Ļæł·å°±
    -0.07
     dagegen
    -0.07
    è¿Ļæł·è¯´
    -0.07
    POSITIVE LOGITS
    ï¼Į
    0.09
     ÙĥÙĦÙĩ
    0.08
    ï¼Į“
    0.08
    ĩ
    0.07
    forth
    0.07
    eters
    0.07
     ìĿ¸íķ´
    0.07
    à´Łàµįà´Ł
    0.07
    ØĮ
    0.07
    ,
    0.07
    Activations Density 0.130%

    No Known Activations