© 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. 44361
    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
    ansa
    -0.06
    à¹īà¸Ńม
    -0.06
     alike
    -0.06
    ëŁŃ
    -0.06
    å¨ħ
    -0.06
    quis
    -0.06
    沫
    -0.06
     pornos
    -0.06
     Kha
    -0.06
    .vocab
    -0.06
    POSITIVE LOGITS
     unspecified
    0.09
    ÙĦاÙĨ
    0.08
    åħ·ä½ĵæĿ¥è¯´
    0.07
     reportedly
    0.07
    имеÑĢ
    0.07
    JC
    0.07
     presumably
    0.07
    JM
    0.07
    odon
    0.07
    antan
    0.07
    Activations Density 0.000%

    No Known Activations