© 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. 8447
    Prev
    Next
    INDEX
    Explanations

    treaty, agreement, deal, wave

    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
    åİ»åĮ»éĻ¢
    -0.10
    ä¹°ä¸ľè¥¿
    -0.09
    ä¸įåĩĨ
    -0.09
     laps
    -0.09
    ç¾½
    -0.09
    æ±´
    -0.09
    ç´§çĽ¯
    -0.09
    oks
    -0.09
    arris
    -0.09
    认
    -0.09
    POSITIVE LOGITS
    æł¸çĶµ
    0.11
     маÑģÑĤ
    0.10
    太éĺ³
    0.09
    ermen
    0.09
    è°¦
    0.08
    ä¹Ŀå·ŀ
    0.08
    æł¸
    0.08
    åºŀ
    0.08
    kle
    0.08
    éĢļæĬ¥
    0.08
    Activations Density 0.046%

    No Known Activations