© 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. 51479
    Prev
    Next
    INDEX
    Explanations

    collaboration and joint efforts

    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
     ساب
    -0.09
    迹
    -0.09
    çŃĩ
    -0.08
    å¸ĪåħĦ
    -0.08
    ANTE
    -0.08
    åħļçļĦé¢Ĩ导
    -0.08
    .untracked
    -0.08
    tring
    -0.08
    ippi
    -0.08
    ssc
    -0.08
    POSITIVE LOGITS
    æķ£å¸ĥ
    0.09
    å¼Ģå±ķ
    0.09
    使人
    0.09
    æĺİæľĹ
    0.09
    æ¨¡æł·
    0.09
    æİ¨è¿Ľ
    0.09
    lovak
    0.09
    å¼Ģåıij
    0.08
    æķĪåºĶ
    0.08
    æĶ»åħĭ
    0.08
    Activations Density 0.039%

    No Known Activations