© 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. 40360
    Prev
    Next
    INDEX
    Explanations

    cars, voice, loud, humans, leash, air

    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
    便äºİ
    -0.10
    å®ĺæĸ¹
    -0.09
    æİ¥åĪ°
    -0.09
    è¿ĻåĿĹ
    -0.09
    èįĴ
    -0.09
    chr
    -0.08
    ÑĩÑĥв
    -0.08
    æī¿æĭħ
    -0.08
    æģ¶
    -0.08
    èĺ¸
    -0.08
    POSITIVE LOGITS
    éĻĮçĶŁ
    0.10
    éĻĮçĶŁäºº
    0.10
    azzi
    0.10
    åĸĦæĦı
    0.10
    åħ¥åı£
    0.09
    implements
    0.09
    çĬį
    0.09
     lạ
    0.09
    èĭķ
    0.08
    -roll
    0.08
    Activations Density 0.099%

    No Known Activations