© 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. 29594
    Prev
    Next
    INDEX
    Explanations

    screen resolution and pixel density

    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
    ogh
    -0.09
    åĨĴ
    -0.09
    æ³ķåĪ¶
    -0.09
     Ign
    -0.08
    æĪ´
    -0.08
    å¾®éĩıåħĥç´ł
    -0.08
    weights
    -0.08
    å½¹
    -0.08
     Coco
    -0.08
    ç¥ļ
    -0.08
    POSITIVE LOGITS
    ç®ħ
    0.09
    çĪ
    0.09
    趸
    0.09
    ç¼®
    0.09
    çĥĤ
    0.09
    SQ
    0.09
    çĤĴèĤ¡
    0.09
    家ä½ı
    0.09
    ç»Ļ人
    0.09
    èĻı
    0.09
    Activations Density 0.007%

    No Known Activations