© 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. 12384
    Prev
    Next
    INDEX
    Explanations

    del

    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
    Monkey
    -0.09
    æ²Ĥ
    -0.09
    è¿Ļåĩł
    -0.09
    ivet
    -0.09
    èĶ¼
    -0.08
     sharp
    -0.08
    åĬłä»¥
    -0.08
    åĮı
    -0.08
    sharp
    -0.08
    ByExample
    -0.08
    POSITIVE LOGITS
    ä»ĸä»¬åľ¨
    0.09
    ven
    0.09
    ect
    0.09
    追溯
    0.08
    leur
    0.08
    est
    0.08
    åįıè°ĥ
    0.08
    æĿĤå¿Ĺ
    0.08
     Lansing
    0.08
    estr
    0.08
    Activations Density 0.053%

    No Known Activations