© 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. 60773
    Prev
    Next
    INDEX
    Explanations

    originals or documents

    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
    åĹ£
    -0.09
    åıijå¸ĥçļĦ
    -0.09
    ä¸Ģ个个
    -0.08
    ä¸ĢæĹ¥
    -0.08
    ä¸Ģ棵
    -0.08
    俯
    -0.08
    åıijå¸ĥ
    -0.08
    åıijå¸ĥäºĨ
    -0.08
    è¾ĵéĢģ
    -0.08
    é£İçŃĿ
    -0.08
    POSITIVE LOGITS
    åİŁä»¶
    0.11
    ä»»ä½ķå½¢å¼ı
    0.10
     originals
    0.10
    å¤įåį°ä»¶
    0.10
     incon
    0.10
    è®®äºĭ
    0.09
    #__
    0.09
    çķĻåŃĺ
    0.09
    åĬ«
    0.09
    å®Į好
    0.09
    Activations Density 0.043%

    No Known Activations