© 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. 26212
    Prev
    Next
    INDEX
    Explanations

    newer

    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
    _finish
    -0.09
    ÙĪا
    -0.08
    IVEN
    -0.08
    åįĥåı¤
    -0.08
    飨
    -0.08
    jian
    -0.08
    åĨľåī¯
    -0.08
    ãģ¾ãģ¾
    -0.08
    future
    -0.08
     Zuk
    -0.08
    POSITIVE LOGITS
    scape
    0.10
    iez
    0.09
     newer
    0.09
    ìĹĶ
    0.09
    å°ijè§ģ
    0.09
    raj
    0.09
    åĮħ袱
    0.09
    йÑĤ
    0.08
     gag
    0.08
    ANEL
    0.08
    Activations Density 0.055%

    No Known Activations