© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17106
    Prev
    Next
    INDEX
    Explanations

    TV show and book series titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    lug
    -0.23
     Rear
    -0.20
    /std
    -0.19
    ammers
    -0.19
    Cargo
    -0.19
    ÐIJÐĿ
    -0.18
     Beans
    -0.18
    è´Ŀ壳
    -0.18
    å¤ĩèĢĥ
    -0.18
    íĭ±
    -0.18
    POSITIVE LOGITS
    åħ¨åİ¿
    0.21
    åİ¿å§Ķ
    0.20
    澧
    0.19
     legalized
    0.19
     County
    0.18
    ç§Ń
    0.18
    åĩĿ
    0.18
    æ¶Ķ
    0.18
    oran
    0.18
    .DataContext
    0.18
    Activations Density 0.001%

    No Known Activations