© 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. 26032
    Prev
    Next
    INDEX
    Explanations

    Washington state or related locations

    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
    oran
    -0.10
    æ¯į
    -0.10
    æ·±åĮĸæĶ¹éĿ©
    -0.10
    æĭį
    -0.09
    åħ¨çIJĥç»ıæµİ
    -0.09
    åĩij
    -0.09
    ç³ħ
    -0.09
     TRE
    -0.09
    iez
    -0.09
    azy
    -0.09
    POSITIVE LOGITS
    çľģå§Ķ
    0.09
    å¤ļåľ°
    0.09
    주ìĿĺ
    0.09
    æ±Łå±±
    0.09
    å¢ĥ
    0.09
     legislature
    0.08
    éĩijåĪļ
    0.08
    <State
    0.08
    -state
    0.08
    å¸ĪèĮĥ大åѦ
    0.08
    Activations Density 0.160%

    No Known Activations