© 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. 47417
    Prev
    Next
    INDEX
    Explanations

    replacement parts and items

    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
    istic
    -0.09
    onaut
    -0.09
    èİŀ
    -0.09
    ä¾µçĬ¯
    -0.09
    羣缸
    -0.08
    æľ«
    -0.08
    hart
    -0.08
    ç£Ķ
    -0.08
    çĶŁäº§åİĤ家
    -0.08
    èĶ¼
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
    ainting
    0.09
    们
    0.09
    .GetResponse
    0.09
    éĢļçŁ¥ä¹¦
    0.09
    èĩªå¦Ĥ
    0.08
     повÑĭ
    0.08
    奥æŀĹåĮ¹
    0.08
    chs
    0.08
    anus
    0.08
    Activations Density 0.016%

    No Known Activations