© 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. 63770
    Prev
    Next
    INDEX
    Explanations

    learn how to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    entrant
    -0.09
    æĪijä¹Ł
    -0.09
    çł¾
    -0.09
    ael
    -0.09
    odor
    -0.08
    URY
    -0.08
    æ··
    -0.08
     Circus
    -0.08
    溪
    -0.08
     sez
    -0.08
    POSITIVE LOGITS
     about
    0.12
    about
    0.09
    ä¾ij
    0.08
    继ç»Ńä¿ĿæĮģ
    0.08
    绾
    0.08
    åıĪ好
    0.08
    缴èIJ¥
    0.08
    å¤ļåIJĥ
    0.08
     tentang
    0.08
    åIJįçīĮ
    0.08
    Activations Density 0.015%

    No Known Activations