© 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. 731
    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
    éĩijçŁ³
    -0.07
    idos
    -0.07
    æ¡£
    -0.07
    æŁ¥å®ŀ
    -0.06
    ÑĢана
    -0.06
    eff
    -0.06
    尽管å¦ĤæѤ
    -0.06
     ((__
    -0.06
    æģ¯
    -0.06
    okens
    -0.06
    POSITIVE LOGITS
    åıĪåı«
    0.09
    åıĪåIJį
    0.08
    аÑĢе
    0.08
    çĻ¾è®¡
    0.08
    /AFP
    0.07
    ugo
    0.07
    asih
    0.07
    åıĪ称
    0.07
    .bg
    0.07
    ayah
    0.07
    Activations Density 0.350%

    No Known Activations

    This feature has no known activations.