© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    measurements and calculating values

    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
    TestCategory
    -0.09
    éĵ¶å±±
    -0.08
    åħ¸åŀĭ
    -0.08
     пÑĢодолжаеÑĤÑģÑı
    -0.08
     mão
    -0.08
    anean
    -0.08
     ÅŁekl
    -0.08
    æľ¬é¢ĺåĪĨæŀIJ
    -0.08
    èĢĮæĺ¯åĽłä¸º
    -0.08
    à¹Ħมà¹Īà¸ĸึà¸ĩ
    -0.08
    POSITIVE LOGITS
     measurement
    0.11
    æµĭéĩı
    0.10
     measurements
    0.10
     measuring
    0.10
     измеÑĢÑı
    0.09
     Measurement
    0.09
    è¡¡éĩı
    0.09
    计ç®Ĺåħ¬å¼ı
    0.09
    æµĭéĩıçļĦ
    0.09
    åħ¬å¼ı
    0.09
    Activations Density 0.050%

    No Known Activations