© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3181
    Prev
    Next
    INDEX
    Explanations

    Hall of Fame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    obody
    -0.23
    лин
    -0.23
    JoinColumn
    -0.22
    orting
    -0.22
    itten
    -0.22
    SSION
    -0.22
    otec
    -0.21
    antly
    -0.21
    çļĦçľ¼ç¥ŀ
    -0.21
    ä¸Ģå¼ł
    -0.21
    POSITIVE LOGITS
     roku
    0.26
    åħĪéĶĭ
    0.25
    à¹ģห
    0.25
    xfb
    0.23
    åĴĮæĬĢæľ¯
    0.23
     laure
    0.23
    声èªī
    0.23
    迹
    0.22
    fax
    0.22
     gaz
    0.22
    Activations Density 0.003%

    No Known Activations