© 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. 64138
    Prev
    Next
    INDEX
    Explanations

    in, on, at

    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
    åħļåĨħ
    -0.10
    è¥Ł
    -0.09
    å¤Ħæĸ¹
    -0.09
    æĴŃæĬ¥
    -0.09
    å°¼äºļ
    -0.08
    æľīç§į
    -0.08
    æĤ²åĵĢ
    -0.08
     леÑĩ
    -0.08
    éĢ¼
    -0.08
    eton
    -0.08
    POSITIVE LOGITS
    æ¼ı
    0.09
    ç«¥
    0.09
    /apt
    0.09
    èıģ
    0.09
    wright
    0.09
    wik
    0.09
    尽快
    0.09
    èħĬ
    0.09
    lapping
    0.09
    stitial
    0.09
    Activations Density 0.316%

    No Known Activations