© 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. 20807
    Prev
    Next
    INDEX
    Explanations

    was / were / did before

    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
    èĥŃ
    -0.10
    ech
    -0.10
    æĴ©
    -0.10
    éºĴ
    -0.09
    ç¯ĵ
    -0.09
    åħ½
    -0.09
    çĸ¤
    -0.09
    ä½°
    -0.09
    å¦Ĥä»Ĭ
    -0.09
     nowadays
    -0.09
    POSITIVE LOGITS
    åĪĿ次
    0.10
    红åĪ©
    0.09
    OrDefault
    0.09
    æĥ¯
    0.09
    æľīè¿ĩ
    0.08
    éĺµéĺµ
    0.08
    ½æķ°
    0.08
    çĮ·
    0.08
    è¿ij两年
    0.08
    ×Ļ×ĵ×Ļ
    0.08
    Activations Density 0.028%

    No Known Activations