© 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. 44621
    Prev
    Next
    INDEX
    Explanations

    office and working environments

    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
    çĽijæĬ¤äºº
    -0.09
    åħĥ宵
    -0.08
    /channel
    -0.08
    ypsy
    -0.08
    canf
    -0.08
    èĢģçĻ¾å§ĵ
    -0.08
    è´«
    -0.07
    åĩºéĻ¢
    -0.07
    uards
    -0.07
    essian
    -0.07
    POSITIVE LOGITS
    åĬŀåħ¬
    0.16
     office
    0.16
    Office
    0.14
    -office
    0.13
     оÑĦиÑģ
    0.13
     Office
    0.13
     offices
    0.13
    office
    0.13
    åĬŀåħ¬å®¤
    0.12
    èģĮåľº
    0.12
    Activations Density 0.304%

    No Known Activations