© 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. 51965
    Prev
    Next
    INDEX
    Explanations

    shipping, store, server, exchange, company

    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
    èĩªæķij
    -0.09
    ä¸Ģ年级
    -0.09
     coli
    -0.08
    å´¦
    -0.08
    aler
    -0.08
    æ¶Īæģ¯ç§°
    -0.08
    èĤ´
    -0.08
    yle
    -0.08
    agger
    -0.08
    ses
    -0.08
    POSITIVE LOGITS
    held
    0.11
    orris
    0.10
    æģ¼
    0.10
    çľ¼ä¸Ń
    0.09
    æ¸ħæ°´
    0.09
    åŁºåľ°
    0.09
    ä»ĵåºĵ
    0.09
    æ½ľæ°´
    0.08
    æŁIJç§įç¨ĭ度
    0.08
    èĢ½è¯¯
    0.08
    Activations Density 0.011%

    No Known Activations