© 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. 51957
    Prev
    Next
    INDEX
    Explanations

    working for

    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
    -twitter
    -0.09
    ä»įçĦ¶æĺ¯
    -0.08
    gradation
    -0.08
    çľ¯
    -0.08
    æ¶Įçİ°
    -0.08
    èĦĨ
    -0.08
    weit
    -0.08
    è¶ģ
    -0.08
    æīĭç»Ń
    -0.08
    MESS
    -0.08
    POSITIVE LOGITS
    ä¹ŁæĽ¾
    0.14
    åģļè¿ĩ
    0.14
    åħĪåIJİ
    0.12
    æĽ¾
    0.12
    ä»ĸæĽ¾
    0.11
    æľīè¿ĩ
    0.10
    ç»ıåİĨè¿ĩ
    0.10
    æĽ¾åľ¨
    0.10
    å¥ĭæĸĹ
    0.10
    å¤ļ家
    0.09
    Activations Density 0.115%

    No Known Activations