© 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. 16743
    Prev
    Next
    INDEX
    Explanations

    Mustang, Horse, Yosemite, Pillow

    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
    家ä¼Ļ
    -0.10
    ONY
    -0.09
    orent
    -0.09
    zie
    -0.09
    èįĩ
    -0.09
    çĿ¬
    -0.09
    kad
    -0.08
    jure
    -0.08
    ulus
    -0.08
    onym
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.10
    iveness
    0.09
    htag
    0.09
    sWith
    0.09
    forth
    0.09
    iOS
    0.09
    /or
    0.09
    pal
    0.09
     Vader
    0.08
    æķĸ
    0.08
    Activations Density 0.004%

    No Known Activations