© 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. 37442
    Prev
    Next
    INDEX
    Explanations

    days of the week or above

    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
    åºľ
    -0.07
    вал
    -0.07
    ä¸Ģå²ģ
    -0.07
     commissioned
    -0.07
     Imag
    -0.06
     lawy
    -0.06
    å½ĵæĪij
    -0.06
    ات
    -0.06
    ELA
    -0.06
    ugat
    -0.06
    POSITIVE LOGITS
    à¸Ļีà¹īà¹Ħà¸Ķà¹ī
    0.08
    à¸Ļีà¹īà¸Ń
    0.08
    à¸Ļีà¹īà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    çļĦè¿Ļä¸Ģ
    0.07
    .this
    0.07
    è¿Ļçķª
    0.07
    à¸Ļีà¹ī
    0.07
    eron
    0.07
     this
    0.06
    èĩ³æѤ
    0.06
    Activations Density 0.006%

    No Known Activations