© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21186
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    ÑĢÑĥÑĩ
    -0.10
    ä¸įä¹ı
    -0.09
    .rs
    -0.09
     Kemp
    -0.09
    å¥ī
    -0.09
    æĪijå·²ç»ı
    -0.08
    èĥİ
    -0.08
     fal
    -0.08
    åħĢ
    -0.08
     tam
    -0.08
    POSITIVE LOGITS
    æĮ¯åħ´
    0.11
    æĽ´å¤ļä¿¡æģ¯
    0.10
    çĸ¥
    0.09
    baum
    0.09
    æķijæµİ
    0.09
    AJOR
    0.09
    éĩį大
    0.09
    ADER
    0.09
    æľ¬è½®
    0.09
    ajor
    0.09
    Activations Density 0.046%

    No Known Activations