© 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. 589
    Prev
    Next
    INDEX
    Explanations

    foreigners

    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
    åģ¥
    -0.09
    梵
    -0.09
    ä¸ī年级
    -0.08
     reaction
    -0.08
    书ä¸Ń
    -0.08
    reaction
    -0.08
    é²ģè¿ħ
    -0.08
     crystals
    -0.08
     equipment
    -0.08
     crystall
    -0.08
    POSITIVE LOGITS
    ä¸ĸ家
    0.11
    缺éĻ·
    0.10
    èĵģ
    0.10
    å°¼æĸ¯
    0.09
     Suffolk
    0.09
    æĻ®åıĬ
    0.08
    @m
    0.08
     Britann
    0.08
    å¹¿æ³ĽåºĶçĶ¨
    0.08
    ãģ§ãģįãģ¦
    0.08
    Activations Density 0.034%

    No Known Activations