© 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. 24097
    Prev
    Next
    INDEX
    Explanations

    signature characteristic

    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
    SupportActionBar
    -0.10
    łģ
    -0.09
    opy
    -0.09
    ech
    -0.09
    ationToken
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    isoft
    -0.08
    æĨ¬
    -0.08
    bic
    -0.08
    á»ĭch
    -0.08
    POSITIVE LOGITS
    ç¬ij容
    0.09
    å¾®ç¬ij
    0.09
    è¡Įäºĭ
    0.09
    ä¹ĭä½ľ
    0.09
    åŀĤ
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.08
    ing
    0.08
    ONT
    0.08
    iest
    0.08
    çŃ¾åIJį
    0.08
    Activations Density 0.009%

    No Known Activations