© 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. 58971
    Prev
    Next
    INDEX
    Explanations

    rounding to million

    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
    oney
    -0.08
    Ģ
    -0.07
    å°ıé»Ħ
    -0.07
    èĪ
    -0.07
     lâm
    -0.06
    çĭ
    -0.06
    akas
    -0.06
    å°½åľ¨
    -0.06
    ogui
    -0.06
    ahas
    -0.06
    POSITIVE LOGITS
    stry
    0.08
    LOTS
    0.08
    èµĦæĸĻæĺ¾ç¤º
    0.07
    imps
    0.07
     endings
    0.07
    üns
    0.07
    å¾Ĺ失
    0.07
    麾ä¸ĭ
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
    imap
    0.07
    Activations Density 0.016%

    No Known Activations