© 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. 44843
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and programming structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ÑĢÑĥбе
    -0.08
     rings
    -0.06
    åħīçĽĺ
    -0.06
     rew
    -0.06
    主干
    -0.06
    rint
    -0.06
    robe
    -0.06
    μβ
    -0.06
    åİŁæĸĩéĵ¾æİ¥
    -0.06
    微信æī«çłģ
    -0.06
    POSITIVE LOGITS
    åĩºèį·
    0.08
    éŁŃ
    0.07
    udu
    0.07
    agam
    0.07
    åĵ¥çļĦ
    0.07
    åĩºçĶŁçļĦ
    0.07
    aised
    0.07
    缸åıįçļĦ
    0.07
     extremes
    0.07
    å·¥åķĨ管çIJĨ
    0.07
    Activations Density 0.005%

    No Known Activations