© 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. 37001
    Prev
    Next
    INDEX
    Explanations

    period or stage

    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
    ä¸İæŶ
    -0.10
    éĿĵ
    -0.09
    å¿ĥä¸Ń
    -0.09
    没æľīæĥ³åĪ°
    -0.08
    è½»è½»åľ°
    -0.08
    ãĥIJãĥĥãĤ¯
    -0.08
    æļĸæ°Ķ
    -0.08
    å¨ĺ
    -0.08
    sched
    -0.08
     Ùĥب
    -0.08
    POSITIVE LOGITS
    æĹ¶æľŁ
    0.30
    éĺ¶æ®µ
    0.29
    æĹ¶æľŁçļĦ
    0.26
    æĻĤæľŁ
    0.22
    æľŁ
    0.21
    éļİ段
    0.20
     phase
    0.20
    æľŁåĨħ
    0.19
     ÑįÑĤап
    0.19
     period
    0.18
    Activations Density 0.165%

    No Known Activations