© 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. 20396
    Prev
    Next
    INDEX
    Explanations

    natural

    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¸įåģľçļĦ
    -0.09
    产ä¸ļåĽŃ
    -0.09
    ä¹ĭåŁİ
    -0.09
    åĽ½å®¶æĪĺçķ¥
    -0.09
    åĤ¨èĥ½
    -0.09
    _IA
    -0.09
    éĵ¿
    -0.09
    æĥľ
    -0.08
    空åīį
    -0.08
    深度
    -0.08
    POSITIVE LOGITS
    天çĦ¶
    0.19
    èĩªçĦ¶
    0.19
     natural
    0.18
    natural
    0.18
     naturally
    0.18
    Natural
    0.16
     Natural
    0.15
     natur
    0.14
     Naturally
    0.13
    aturally
    0.13
    Activations Density 0.095%

    No Known Activations