© 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. 37702
    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
    jal
    -0.08
    æ¯Ķ以åīį
    -0.08
    asiun
    -0.08
    å¾Ĺæľī
    -0.08
     integrato
    -0.08
    ÑĤÑĩ
    -0.08
    HOOK
    -0.07
     Setia
    -0.07
    ä¸ĭ游
    -0.07
     едино
    -0.07
    POSITIVE LOGITS
    è¾ĥçŁŃ
    0.08
    åıĸåħ¶
    0.08
    å°ıäºİ
    0.07
     shorter
    0.07
    åĴĮå¹³
    0.06
    ç¿»
    0.06
     opposite
    0.06
     (<
    0.06
    utr
    0.06
    常è§Ħ
    0.06
    Activations Density 0.000%

    No Known Activations