© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22134
    Prev
    Next
    INDEX
    Explanations

    director following words like 'a', 'an', 'is'

    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
    ilas
    -0.07
     Bulk
    -0.07
     exchanged
    -0.06
    etra
    -0.06
    åŃĺæĶ¾
    -0.06
     bulk
    -0.06
    èĩªæĭĶ
    -0.06
    eby
    -0.06
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļà¹Į
    -0.06
     khá»ķng
    -0.06
    POSITIVE LOGITS
    æī§å¯¼
    0.15
     ê°IJëıħ
    0.10
    åŁ·
    0.09
    æĮĩæĮ¥
    0.09
    çĽ£çĿ£
    0.09
    å¤Ħ女
    0.09
    带éĺŁ
    0.09
     helm
    0.08
    æĮĩ导ä¸ĭ
    0.08
    director
    0.08
    Activations Density 0.279%

    No Known Activations