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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4182
    Prev
    Next
    INDEX
    Explanations

    suffering or affected group

    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
    æ¬²æľĽ
    -0.09
    æħİ
    -0.09
    åĵ¨
    -0.09
    对åѦçĶŁ
    -0.09
    åĪ¶æŃ¢
    -0.09
     пÑĢидеÑĤÑģÑı
    -0.09
    è¡Į车
    -0.09
    ODB
    -0.09
    å°ıå¿ĥ翼翼
    -0.09
     Oswald
    -0.09
    POSITIVE LOGITS
     quar
    0.10
    æĹłåĬĽ
    0.10
    失åİ»
    0.09
    æļĤæŶ
    0.09
    ä¹ĭ人
    0.09
    åĪ°è¿ĻéĩĮ
    0.08
    تز
    0.08
    éĴĬ
    0.08
    æĢ¥éľĢ
    0.08
    失
    0.08
    Activations Density 0.133%

    No Known Activations