© 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. 65382
    Prev
    Next
    INDEX
    Explanations

    technical challenges and improvements

    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
    åİĮ
    -0.08
    轻轻
    -0.07
    轻微
    -0.07
    å¹³æŶ
    -0.07
     verbal
    -0.07
    ä½ľçĶ¨
    -0.06
    å¿ĺ
    -0.06
     ward
    -0.06
    oko
    -0.06
     appos
    -0.06
    POSITIVE LOGITS
    缮åīįçļĦ
    0.11
    åħ³éĶ®æĬĢæľ¯
    0.10
    çĵ¶é¢Ī
    0.10
     breakthrough
    0.10
    éĩı产
    0.10
    æĶ»åħ³
    0.10
    æĺ¯çĽ®åīį
    0.09
    产ä¸ļåĮĸ
    0.09
     bottleneck
    0.09
    çİ°æľīæĬĢæľ¯
    0.09
    Activations Density 0.301%

    No Known Activations