© 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. 34758
    Prev
    Next
    INDEX
    Explanations

    apologize, correct errors, or volunteer

    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
    åĿļå®ļäºĨ
    -0.08
    inton
    -0.08
    zeug
    -0.08
    çŁŃè¯Ħ
    -0.08
    ĥĿ
    -0.08
    </think>
    -0.08
    à¹Īาà¸ĩ
    -0.08
    åģ¥åº·å¿«ä¹IJ
    -0.08
    è½°è½°çĥĪ
    -0.08
    entai
    -0.08
    POSITIVE LOGITS
     goodwill
    0.11
    主åĬ¨
    0.11
     voluntarily
    0.11
    åĸĦå¾ħ
    0.11
     generosity
    0.10
    ä¸įå¿į
    0.10
    åıĭ好
    0.10
    å°Ĭéĩį
    0.10
    ç¼ĵåĴĮ
    0.10
     generous
    0.09
    Activations Density 0.281%

    No Known Activations