© 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. 51804
    Prev
    Next
    INDEX
    Explanations

    recent years

    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
    å½ĵåĪĿ
    -0.11
    æŃ¤æ¬¡
    -0.10
    æľ¬æ¬¡
    -0.10
    å½ĵæŶ
    -0.10
    ált
    -0.10
    çİ°åľ¨çļĦ
    -0.10
    æĹ©æĹ¥
    -0.09
    è¿ĻçĤ¹
    -0.09
    unger
    -0.09
    è¿Ļä¸ĢçĤ¹
    -0.09
    POSITIVE LOGITS
    ãĢħ
    0.10
    ä¸įä¹ı
    0.09
    åħ´èµ·
    0.09
    nej
    0.09
    乱象
    0.09
    oso
    0.08
    大çīĩ
    0.08
    é¢ĩæľī
    0.08
     Hague
    0.08
    æĶ¯çº¿
    0.08
    Activations Density 0.032%

    No Known Activations