© 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. 59209
    Prev
    Next
    INDEX
    Explanations

    scores and sets

    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
    ä¹ŁçŁ¥éģĵ
    -0.09
     tim
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    大家ä¸Ģèµ·
    -0.08
    å¹²åĺĽ
    -0.08
    æĹłèģĬ
    -0.08
    åģļ强
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    åħ¨æ°ij
    -0.08
    onda
    -0.08
    POSITIVE LOGITS
    ORK
    0.09
    顶å±Ĥ
    0.08
    ç¢İ
    0.08
    溱
    0.08
    ç§įç§į
    0.08
    ork
    0.08
    icum
    0.08
     ÑģÑĤоиÑĤ
    0.08
    ActionResult
    0.08
    ikk
    0.08
    Activations Density 0.041%

    No Known Activations