© 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. 8966
    Prev
    Next
    INDEX
    Explanations

    as [followed by subject verb]

    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
    -bin
    -0.10
    èĩªä»İ
    -0.10
    à¤Ľ
    -0.10
    æľĢéĢĤåIJĪ
    -0.10
    æĸ¯åŁº
    -0.09
    èµĦ
    -0.09
    åĽłä¸ºä»ĸ
    -0.09
    çīĪ
    -0.09
    ÑĢеги
    -0.09
    æľĢåıĹ欢è¿İ
    -0.08
    POSITIVE LOGITS
    æ»ļåĬ¨
    0.10
    ä¸įæĸŃåľ°
    0.10
    æİ¥è¿ij
    0.08
    åݦ
    0.08
    æıIJæĭĶ
    0.08
    åĵŃäºĨ
    0.08
    hort
    0.08
    cert
    0.08
    ç¿ķ
    0.08
    è§Ĩ线
    0.08
    Activations Density 0.072%

    No Known Activations