© 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. 16384
    Prev
    Next
    INDEX
    Explanations

    "Just" followed by quote

    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
    imum
    -0.08
    âĸ½
    -0.08
    andle
    -0.07
    à´¿à´²
    -0.07
    尼奥
    -0.07
    ikal
    -0.07
    ToProps
    -0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    -0.07
     **:**
    -0.07
    à¹īà¸ĩ
    -0.07
    POSITIVE LOGITS
    ↵↵
    0.17
     ↵↵
    0.12
      ↵↵
    0.09
            ↵↵
    0.09
                    ↵↵
    0.09
    	↵↵
    0.08
         ↵↵
    0.08
          ↵↵
    0.08
       ↵↵
    0.08
           ↵↵
    0.08
    Activations Density 0.428%

    No Known Activations