© 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. 26346
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    bole
    -0.10
    æĭŃ
    -0.09
    ä¸Ģ线
    -0.08
    pcb
    -0.08
    bject
    -0.08
    oris
    -0.08
     bo
    -0.08
     COD
    -0.08
    æѤæĸĩ
    -0.07
    pc
    -0.07
    POSITIVE LOGITS
    åįĩèµ·
    0.09
    çľ¼è§Ĵ
    0.09
    æĤłæĤł
    0.09
    egrity
    0.09
    ç¨Ģ
    0.09
    unity
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.09
    éĤ£æ®µ
    0.09
    tle
    0.08
    çĩ®
    0.08
    Activations Density 0.000%

    No Known Activations