© 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. 16652
    Prev
    Next
    INDEX
    Explanations

    test plan, report, or case

    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
    åIJĪä½ľ
    -0.09
    çļĦåIJĪä½ľ
    -0.08
     Hav
    -0.08
     Marg
    -0.08
    Inset
    -0.08
    aksi
    -0.08
    çłĮ
    -0.08
    acted
    -0.08
     Emil
    -0.08
    污
    -0.08
    POSITIVE LOGITS
    stem
    0.09
    å®ļéĩı
    0.09
    modifiable
    0.09
    诮
    0.09
    .await
    0.09
    轩è¾ķ
    0.09
    å¾Ĥ
    0.09
    ngen
    0.09
    èijī
    0.08
     Stem
    0.08
    Activations Density 0.090%

    No Known Activations