© 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. 59435
    Prev
    Next
    INDEX
    Explanations

    missed items, events, or information

    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
    èĥľä»»
    -0.09
    触åıĬ
    -0.09
    ä¸Ģå¹ħ
    -0.08
    _successful
    -0.08
    æĵį
    -0.08
    éĺĬ
    -0.08
    osg
    -0.08
    å±ķå¼Ģ
    -0.08
    erman
    -0.08
    dance
    -0.08
    POSITIVE LOGITS
    tes
    0.11
    AFE
    0.09
     altogether
    0.09
     Templ
    0.09
    à¹Ĥà¸ŀ
    0.09
    主ä½ĵ
    0.09
    åİŁæľīçļĦ
    0.08
    ç¹ģåįİ
    0.08
    对ä»ĸ们
    0.08
    æ¯ķ
    0.08
    Activations Density 0.059%

    No Known Activations