© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16750
    Prev
    Next
    INDEX
    Explanations

    Washington (followed by punctuation)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    волÑĮ
    -0.09
    å·į
    -0.09
    å··
    -0.09
    å¨ģå°Ķ
    -0.09
    çļĦæĥħæĦŁ
    -0.09
    çļĦåĪ°æĿ¥
    -0.09
    èĽ®
    -0.09
    æ´±
    -0.08
    å´Ń
    -0.08
    èĢģ人家
    -0.08
    POSITIVE LOGITS
     Wash
    0.10
    鸿
    0.09
    uator
    0.09
    Ñīа
    0.08
    éĨī
    0.08
     Pist
    0.08
    éĢĤæŶ
    0.08
    Playable
    0.08
    quence
    0.08
    åįĬå¤ľ
    0.08
    Activations Density 0.022%

    No Known Activations