© 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. 3189
    Prev
    Next
    INDEX
    Explanations

    theatre, reviews, titles, or numbers

    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
    è°ģçŁ¥éģĵ
    -0.24
    åĴ§
    -0.24
    ær
    -0.23
    ãĤ
    -0.23
    fur
    -0.23
     NEVER
    -0.23
    EGA
    -0.23
    åķª
    -0.23
    ardy
    -0.22
     NotImplemented
    -0.22
    POSITIVE LOGITS
     debut
    0.31
    æĢ»ä½ĵ
    0.28
    让æĪij
    0.28
     admirable
    0.28
     impressive
    0.27
     remarkable
    0.27
    åľ¨æĪijçľĭæĿ¥
    0.27
    çļĦåĬ¨ä½ľ
    0.25
     standout
    0.25
    令人
    0.25
    Activations Density 0.171%

    No Known Activations