© 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. 6258
    Prev
    Next
    INDEX
    Explanations

    dropped / thrown / shot

    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
    arness
    -0.10
     пÑĢÑı
    -0.10
    ä¸įè§ģäºĨ
    -0.09
    aldi
    -0.09
    otos
    -0.09
    åĮĹ约
    -0.09
    æ¼Ķ示
    -0.09
    éĥ¨åĪĨåľ°åĮº
    -0.09
    æį
    -0.09
    ç¡®è¯Ĭ
    -0.09
    POSITIVE LOGITS
    ewed
    0.09
    ç»Ļä½łä»¬
    0.09
    é£ĺ
    0.09
    åĨĴçĿĢ
    0.09
    æ©Ħæ¦Ħ
    0.09
    ije
    0.08
    éľĨ
    0.08
    è¾Ħ
    0.08
    輩
    0.08
    æ¼Ĥ
    0.08
    Activations Density 0.031%

    No Known Activations