© 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. 57726
    Prev
    Next
    INDEX
    Explanations

    economy, sales, claims, forecast, outlook

    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
    æ¯ıå¹´
    -0.09
    æ¯ıå¹´çļĦ
    -0.09
    æ¯ıåŃ¦æľŁ
    -0.08
    èŀįèµĦåİĨç¨ĭ
    -0.07
     yearly
    -0.07
    第äºĮå¹´
    -0.07
     ежегодно
    -0.07
     goog
    -0.07
    åĢºåĪ¸ä¿¡æģ¯
    -0.07
     scop
    -0.07
    POSITIVE LOGITS
    å°ıå¹ħ
    0.10
    ä¹ħè¿Ŀ
    0.09
    é¢ĦæľŁ
    0.09
    ä¼ļ继ç»Ń
    0.08
    é¢Ħ计
    0.08
    å¼ķãģįç¶ļãģį
    0.08
    åĬ¨èĥ½
    0.08
     forecast
    0.08
    expect
    0.08
    éłIJæľŁ
    0.08
    Activations Density 0.511%

    No Known Activations