© 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. 59234
    Prev
    Next
    INDEX
    Explanations

    clause

    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
    çĦ¶æĺ¯
    -0.09
    shire
    -0.08
    allas
    -0.08
    ness
    -0.08
    ĺ
    -0.08
    tant
    -0.08
    .Encode
    -0.08
    دا
    -0.08
    ÙĪع
    -0.08
    ย
    -0.08
    POSITIVE LOGITS
    วย
    0.10
    buster
    0.10
    hound
    0.10
    æ»ĵ
    0.09
    pole
    0.09
    ernal
    0.09
    USTER
    0.09
     жизни
    0.09
     Buster
    0.09
    ç±³å°Ķ
    0.09
    Activations Density 0.008%

    No Known Activations