© 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. 52152
    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
    ë§ŀ
    -0.07
    âĢij
    -0.07
    otos
    -0.07
    âĢIJ
    -0.07
    entas
    -0.07
     zero
    -0.07
    ifar
    -0.07
     uns
    -0.06
    并äºİ
    -0.06
    ੱ
    -0.06
    POSITIVE LOGITS
    大åħ¬
    0.08
    tep
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.07
    áĥ¬áĥ§
    0.07
    setzung
    0.07
    nat
    0.07
    ä¹ĭ士
    0.07
    à¤Ĺत
    0.07
    sis
    0.07
    retty
    0.07
    Activations Density 0.000%

    No Known Activations