© 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. 12302
    Prev
    Next
    INDEX
    Explanations

    keywords, punctuation, code blocks

    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
    4
    -0.11
    6
    -0.10
    5
    -0.10
    8
    -0.10
    7
    -0.10
    9
    -0.10
    æľªç»ıæİĪæĿĥ
    -0.10
    3
    -0.10
    1
    -0.09
    2
    -0.09
    POSITIVE LOGITS
    åĽº
    0.09
    ALSE
    0.09
    梨
    0.09
    .keywords
    0.08
    æĭ¼æIJı
    0.08
    æĥ³åĪ°
    0.08
     Lum
    0.08
    æľĢ大ç¨ĭ度
    0.08
    çĻ¾äº¿
    0.08
     ìĹ
    0.08
    Activations Density 0.052%

    No Known Activations