© 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. 59253
    Prev
    Next
    INDEX
    Explanations

    since the advent of

    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
    æĪijå½ĵæŶ
    -0.10
    åıijåĬĽ
    -0.09
    äººåľ¨
    -0.09
    agger
    -0.09
    ow
    -0.09
    former
    -0.09
    erte
    -0.09
    æĪijçİ°åľ¨
    -0.08
    ä¸ĢçĶŁ
    -0.08
    æĿ¾å¼Ľ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ缴æĺ¯
    0.11
    以ä¾Ĩ
    0.11
    ä¸Ģ缴
    0.11
    ä¸ĢçĽ´åľ¨
    0.10
    ä¸Ģ缴éĥ½
    0.10
    ä¸ĢçĽ´æ²¡æľī
    0.10
    æīįåıijçİ°
    0.10
     ÙĪØŃتÙī
    0.10
    ãģļãģ£ãģ¨
    0.10
    丧
    0.10
    Activations Density 0.044%

    No Known Activations