© 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. 12346
    Prev
    Next
    INDEX
    Explanations

    CGI scripts

    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
    èĥĮåIJİçļĦ
    -0.09
    eting
    -0.09
    Ñıд
    -0.08
     sẵ
    -0.08
    à¹ģ
    -0.08
    chter
    -0.08
    ingo
    -0.08
    åīį身
    -0.08
    ellt
    -0.08
     thá»±
    -0.08
    POSITIVE LOGITS
    ãĤģ
    0.10
    æĮĩæľĽ
    0.09
    çĿ
    0.09
    çķĶ
    0.09
    ../../../
    0.09
    å®ĥ们
    0.09
    avana
    0.09
    æ¶İ
    0.09
    éĺij
    0.08
     Äiju
    0.08
    Activations Density 0.027%

    No Known Activations