© 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. 49027
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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
    ↵↵
    -0.09
        ↵↵
    -0.07
                    ↵↵
    -0.07
     Holl
    -0.06
      ↵↵
    -0.06
    	↵↵
    -0.06
                ↵↵
    -0.06
    ÙĥÙĩ
    -0.06
    et
    -0.06
     ↵↵
    -0.06
    POSITIVE LOGITS
    ogos
    0.07
    urso
    0.07
    assandra
    0.07
    åı¥åı¥
    0.07
    并ç»ĻäºĪ
    0.07
    à§įতà§ģ
    0.07
    zna
    0.07
    lasses
    0.07
     scales
    0.07
    ilar
    0.07
    Activations Density 0.584%

    No Known Activations