© 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. 64141
    Prev
    Next
    INDEX
    Explanations

    free offers

    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
    æĭ³
    -0.09
    orno
    -0.09
    éĿ¢åŃĶ
    -0.09
    draft
    -0.09
    å½¢æĪIJäºĨ
    -0.09
    èĤŁ
    -0.09
    å¼ĵ
    -0.08
    åĪĨéĶĢ
    -0.08
    ä¾Ľç»Ļ
    -0.08
    å·´æĸ¯
    -0.08
    POSITIVE LOGITS
    代
    0.10
    apist
    0.10
    磾
    0.09
    çİ°åľ¨å¾Īå¤ļ
    0.09
     McGr
    0.09
    éĹ´æİ¥
    0.09
    rey
    0.08
    شار
    0.08
    ëģĶ
    0.08
    ìĥĺ
    0.08
    Activations Density 0.012%

    No Known Activations