© 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. 29502
    Prev
    Next
    INDEX
    Explanations

    Washington state and DC contexts

    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
    æįŁèĢĹ
    -0.11
    ç»°
    -0.10
    å°ıåŃIJ
    -0.09
    åŃIJéĩĮ
    -0.09
    çĭ·
    -0.09
    空éĹ´
    -0.09
    ture
    -0.09
    ãĢħ
    -0.09
    ©
    -0.09
    è¹Ń
    -0.08
    POSITIVE LOGITS
     Redskins
    0.10
    å¿į
    0.09
    çī¹æ´¾
    0.09
    ÑĮе
    0.09
     Seattle
    0.09
    ä¸Ģ家
    0.08
    ä¸ĭéĿ¢å°±
    0.08
    ya
    0.08
     DC
    0.08
    ockey
    0.08
    Activations Density 0.037%

    No Known Activations