© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4850
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    人åħ³æ³¨
    -0.09
    ainties
    -0.09
    वल
    -0.09
    .mybatisplus
    -0.08
    ukt
    -0.08
    ÙħاÙĨ
    -0.08
    amentals
    -0.08
    ARSE
    -0.08
    tesy
    -0.08
    undra
    -0.08
    POSITIVE LOGITS
    <|box_end|>
    0.07
    ä¹ĭ为
    0.07
    ãģĦãĤĭ
    0.07
    ÑİÑĤ
    0.07
    еÑĤ
    0.07
    ie
    0.07
    ento
    0.06
    INN
    0.06
    ized
    0.06
    ation
    0.06
    Activations Density 0.000%

    No Known Activations