© 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. 47419
    Prev
    Next
    INDEX
    Explanations

    professional contact information

    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
    andon
    -0.09
     iid
    -0.08
    齡
    -0.07
    寮
    -0.07
    ijkl
    -0.07
    輪
    -0.07
    äºĭ
    -0.07
    æ¬
    -0.07
    atak
    -0.07
    mast
    -0.07
    POSITIVE LOGITS
    çĥŃ线
    0.11
    就说
    0.10
    è°IJ
    0.10
    å°ıå§IJå§IJ
    0.10
    /oct
    0.09
    å°Ŀ
    0.09
    omb
    0.09
    åī¥
    0.09
    çıį
    0.09
    讲æķħäºĭ
    0.09
    Activations Density 0.030%

    No Known Activations