© 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. 55204
    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
    Not in Any Lists

    No Comments

    Negative Logits
    moil
    -0.07
    adari
    -0.07
     Until
    -0.07
    lobal
    -0.07
    .lesson
    -0.07
    )").
    -0.07
    oho
    -0.07
    笤
    -0.07
    —but
    -0.07
    .heroku
    -0.07
    POSITIVE LOGITS
    å¿«åİ»
    0.07
    çµ®
    0.06
    gli
    0.06
    人åħ³æ³¨
    0.06
    éĹĨ
    0.06
    æ£ł
    0.06
    并ä¸įå¤ļ
    0.06
    é«ĺ度éĩįè§Ĩ
    0.06
    åħĭåħ°
    0.06
    åħ¬éĩĮå¤Ħ
    0.06
    Activations Density 0.000%

    No Known Activations