© 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. 10315
    Prev
    Next
    INDEX
    Explanations

    later centuries

    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
    æīĢæľīæĥħèĬĤ
    -0.37
    âīĤ
    -0.36
     salopes
    -0.34
     )↵↵↵↵↵↵↵↵
    -0.34
     pornost
    -0.34
    á¿ij
    -0.33
    hợ
    -0.33
     tjejer
    -0.31
     pornôs
    -0.30
    iéndo
    -0.30
    POSITIVE LOGITS
    è¿ij代
    0.34
    éĤ£æŶåĢĻ
    0.34
    éĤ£æŶ
    0.34
     centuries
    0.31
    æĻļæľŁ
    0.31
     gradual
    0.28
    æĹ©æľŁ
    0.28
     rulers
    0.28
    åı¤ä»£
    0.28
     later
    0.27
    Activations Density 0.182%

    No Known Activations