© 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. 59950
    Prev
    Next
    INDEX
    Explanations

    side effects, sensations, discomfort

    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
    Negative Logits
     doomed
    -0.08
     scandal
    -0.08
    æ²ĥåľŁ
    -0.08
     cripp
    -0.07
    大åĪĢ
    -0.07
     ambigu
    -0.07
    éľĩæĥĬ
    -0.07
     prestigious
    -0.07
    åĨķ
    -0.07
     devastated
    -0.07
    POSITIVE LOGITS
    轻微çļĦ
    0.10
    æĦŁè§ī
    0.10
     sensations
    0.10
     discomfort
    0.10
    轻微
    0.09
     feeling
    0.09
    èµ·åºĬ
    0.09
     bouts
    0.09
    çĹĩçĬ¶
    0.09
    ç»ı绾
    0.08
    Activations Density 0.199%

    No Known Activations