© 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. 52149
    Prev
    Next
    INDEX
    Explanations

    biological entities and processes

    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
    oux
    -0.09
    åħ¨éĥ¨åĨħ容
    -0.09
    åį³åĪ°
    -0.08
     sogar
    -0.08
    åīįè¿°
    -0.08
    åıįåĢĴ
    -0.08
    ä¸įèµ·æĿ¥
    -0.07
    åıįèĢĮ
    -0.07
    idor
    -0.07
    oga
    -0.07
    POSITIVE LOGITS
    åı¯ä»¥åĪĨ为
    0.07
    å®Ŀå®Ŀ们
    0.07
    æľĢæĢķ
    0.07
    éļ¾åħį
    0.07
    ä¸įä»ħéľĢè¦ģ
    0.07
    æĢ»è¦ģ
    0.07
    åı¯åĪĨ为
    0.07
    主è¦ģåĪĨ为
    0.07
    éĥ½åĸľæ¬¢
    0.06
    éĥ½å¸ĮæľĽ
    0.06
    Activations Density 0.216%

    No Known Activations