© 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. 16693
    Prev
    Next
    INDEX
    Explanations

    give us

    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
    lands
    -0.09
    land
    -0.09
    æĬ¤
    -0.08
    uran
    -0.08
    迪士
    -0.08
     Miner
    -0.08
    éĺĩ
    -0.08
    LAND
    -0.08
    FormData
    -0.08
    ìĤ¬ë¥¼
    -0.08
    POSITIVE LOGITS
    èĢĻ
    0.10
    æĪĹ
    0.10
    äºĨä¸Ģ声
    0.09
    éĴī
    0.09
    æ¯ı个
    0.09
    äºĭä¸ļ
    0.09
    roc
    0.09
    èĤłèĥĥ
    0.08
     scm
    0.08
    éĺŁä¼į
    0.08
    Activations Density 0.026%

    No Known Activations