© 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. 26341
    Prev
    Next
    INDEX
    Explanations

    for that reason/matter

    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
    ç´ł
    -0.09
    åıĹ
    -0.09
    è¿Ľåı£
    -0.09
    åį´æ²¡æľī
    -0.09
    è¶´åľ¨
    -0.09
    æĿľåħ°
    -0.08
    ï¸
    -0.08
    åį´è¢«
    -0.08
    åĿİ
    -0.08
    cobra
    -0.08
    POSITIVE LOGITS
    ä¹Łå¥½
    0.13
    ä¸Ģæł·
    0.10
    è¿ĺæľī
    0.09
    çĶļèĩ³
    0.09
    è²Į
    0.09
    æ¼Ķ
    0.08
    ä¹ĥèĩ³
    0.08
     Baghd
    0.08
    åħ¶ä»ĸçļĦ
    0.08
     Rena
    0.08
    Activations Density 0.005%

    No Known Activations