© 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. 60735
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    åı¤
    -0.08
    çĽ¸å¯¹
    -0.08
     contrasting
    -0.08
    åį°
    -0.08
    arro
    -0.08
    轸
    -0.08
    orc
    -0.08
    ArgumentException
    -0.08
    å½ĵä¸ĭ
    -0.08
    ayo
    -0.08
    POSITIVE LOGITS
    åį«è§Ĩ
    0.10
    æ²³æµģåŁŁ
    0.09
    ç¾ģ
    0.09
    èĬĤèĥ½åĩıæİĴ
    0.09
    æľīæĿ¡ä»¶
    0.09
    æĹħ游ä¸ļ
    0.09
    sst
    0.09
    -tabs
    0.09
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.09
    çĥľ
    0.08
    Activations Density 0.021%

    No Known Activations