© 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. 51484
    Prev
    Next
    INDEX
    Explanations

    located in a place

    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
    æµ·è¿IJ
    -0.09
    沦
    -0.09
    椰
    -0.09
    ÑĢин
    -0.09
    èŁ¾
    -0.08
    anos
    -0.08
    æĹłåģ¿
    -0.08
    æ²Ļ滩
    -0.08
    ç´Ģ
    -0.08
    äºĪ
    -0.08
    POSITIVE LOGITS
    峡
    0.09
    èĮ¸
    0.09
    iture
    0.09
    çĿ¦
    0.09
    _aug
    0.09
    ental
    0.08
    çıłä¸īè§Ĵ
    0.08
    å¾ķ
    0.08
    å¨ĥ
    0.08
    çĻ½é©¬
    0.08
    Activations Density 0.171%

    No Known Activations