© 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. 9190
    Prev
    Next
    INDEX
    Explanations

    stick to

    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
    æŶåħī
    -0.10
    ç£ħ
    -0.10
    éĵ¢
    -0.09
    ç¼Ń
    -0.09
    ç«ŁçĦ¶
    -0.09
    é¢Ħå¤ĩ
    -0.08
    PTION
    -0.08
    _HEAP
    -0.08
    éĽĦåİļ
    -0.08
    สาย
    -0.08
    POSITIVE LOGITS
    éĢłçº¸
    0.10
     sticking
    0.09
    æĮ¯
    0.09
     stuck
    0.09
    é¦Ĩ
    0.09
    ä¸ĭåİ»
    0.09
    iol
    0.09
    åĢĶ
    0.08
    æ¯ı个人éĥ½
    0.08
    åĪ°å¤Ħ
    0.08
    Activations Density 0.020%

    No Known Activations