© 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. 26107
    Prev
    Next
    INDEX
    Explanations

    attitudes towards or 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
    大æĪ·
    -0.10
     Moor
    -0.09
    ãĤĪãģĨ
    -0.09
    ä¸Ģ度
    -0.09
    éĻħ
    -0.08
    ing
    -0.08
     Soda
    -0.08
    æĪĺçķ¥å¸ĥå±Ģ
    -0.08
    eric
    -0.08
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.10
    istic
    0.10
    ä¸ĩåįĥ
    0.10
    æ¯Ļ
    0.10
    gne
    0.09
    brains
    0.09
    é«ĺæĺĤ
    0.09
    ÙħÙĨتدÙĬ
    0.09
    geber
    0.09
    åģķ
    0.09
    Activations Density 0.007%

    No Known Activations