© 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. 44328
    Prev
    Next
    INDEX
    Explanations

    any followed by a descriptor

    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
     never
    -0.08
     behalf
    -0.07
    ogne
    -0.07
    endam
    -0.07
    åĽŀäºĭ
    -0.07
    åIJĦå¤Ħ
    -0.07
    ãģ¨ãģĵãĤįãģ§ãģĻ
    -0.06
     {}".
    -0.06
    uestos
    -0.06
    ModifiedDate
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.10
    å·¥ä½ľéľĢè¦ģ
    0.09
    owing
    0.09
    è¿ĻäºĽéĥ½
    0.09
    verages
    0.08
    ledo
    0.08
    è´¹çĶ¨çĶ±
    0.08
    wendungen
    0.07
     تÙĤرÙĬب
    0.07
    çłĶ究表æĺİ
    0.07
    Activations Density 0.033%

    No Known Activations