© 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. 45682
    Prev
    Next
    INDEX
    Explanations

    calculated from

    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
    å¯Ĩæĸ¯
    -0.07
    åij¨æľŁæĢ§
    -0.07
    ersh
    -0.07
    åĨħ容为
    -0.07
    à¸Ľà¸£à¸°
    -0.06
    à¹Ģลยà¹Į
    -0.06
    çī¹çĤ¹æĺ¯
    -0.06
    ipients
    -0.06
    çļĦçī¹çĤ¹æĺ¯
    -0.06
     contin
    -0.06
    POSITIVE LOGITS
     inferred
    0.11
    æł¡åĩĨ
    0.10
     ded
    0.10
     calibration
    0.09
    åħ¬å¼ı
    0.09
     inference
    0.09
    æł¡æŃ£
    0.09
    æݨç®Ĺ
    0.09
     formula
    0.09
     corrected
    0.09
    Activations Density 0.050%

    No Known Activations