© 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. 37672
    Prev
    Next
    INDEX
    Explanations

    both

    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
    ?,?,?,?,
    -0.10
    çݺ
    -0.09
    äºĶ人
    -0.08
    éĤ£äºĽäºº
    -0.08
    ä¸īæĸ¹
    -0.07
    åīįä¸īåIJį
    -0.07
    assi
    -0.07
    åīįä¸ī
    -0.07
    ä¸ī人
    -0.07
    åĽĽäºº
    -0.07
    POSITIVE LOGITS
    è¿Ļ两个
    0.21
    è¿Ļ两
    0.20
    è¿Ļ两ç§į
    0.19
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.18
    éĢĻåħ©åĢĭ
    0.17
     both
    0.17
    both
    0.17
    ãģ©ãģ¡ãĤīãĤĤ
    0.17
    éĢĻåħ©
    0.17
     BOTH
    0.16
    Activations Density 0.398%

    No Known Activations