© 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. 55040
    Prev
    Next
    INDEX
    Explanations

    criticism or opposition

    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
     amazingly
    -0.07
    allback
    -0.06
    ارÙģ
    -0.06
     descans
    -0.06
    çĬ¹è±«
    -0.06
    太好äºĨ
    -0.06
    scrollTop
    -0.06
    ä¼Ł
    -0.06
    ç«ŁçĦ¶
    -0.06
    ansfer
    -0.06
    POSITIVE LOGITS
    æĮĩæijĺ
    0.13
    æī¹è¯Ħ
    0.12
     criticism
    0.11
     critique
    0.10
    åĪĻ认为
    0.10
     criticize
    0.10
     criticisms
    0.10
    ä¸į满
    0.10
     critic
    0.10
     critiques
    0.10
    Activations Density 0.349%

    No Known Activations