© 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. 3314
    Prev
    Next
    INDEX
    Explanations

    bit

    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
    åĴĮæĶ¯æĮģ
    -0.26
    ä¸ĢæŃ¥æŃ¥
    -0.24
    ä»»ä½ķ
    -0.24
    ä¸į管æĺ¯
    -0.24
    ä»»ä½ķ人
    -0.23
    ä¸Ģ个个
    -0.23
    ä¸į论æĺ¯
    -0.23
    大éĩı
    -0.22
    ä¸įæĸŃæıIJåįĩ
    -0.22
    whatever
    -0.22
    POSITIVE LOGITS
    ìĶ©
    0.33
    ewhat
    0.24
     nuances
    0.23
     disconnected
    0.23
     (?)
    0.22
    åĦ¿
    0.22
     shades
    0.21
     немного
    0.21
     overrun
    0.21
    大çļĦ
    0.21
    Activations Density 0.021%

    No Known Activations