© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    health center staff

    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
    çłĶåıijåĽ¢éĺŁ
    -0.08
    ä¸ĭåĨ³å¿ĥ
    -0.07
    çłĶåıijä¸Ńå¿ĥ
    -0.07
    ä¸ĵå®¶åĽ¢éĺŁ
    -0.07
    èģĮä¸ļè§ĦåĪĴ
    -0.07
    åıĤå±ķ
    -0.07
    åħ¨ä½ĵå¹²éĥ¨èģĮå·¥
    -0.07
    æ³»
    -0.07
    éĿ¢åIJijåħ¨åĽ½
    -0.07
    ä¸İåĽ½åĨħ
    -0.07
    POSITIVE LOGITS
    /community
    0.12
    åĴĮ社åĮº
    0.11
    åŁºå±Ĥ
    0.10
    åŁºå±Ĥç»Ħç»ĩ
    0.10
    åľ¨å½ĵåľ°
    0.10
    社åĮº
    0.09
     neighborhood
    0.09
     community
    0.09
     locally
    0.09
    èĩªæ²»
    0.09
    Activations Density 0.109%

    No Known Activations