© 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. 8292
    Prev
    Next
    INDEX
    Explanations

    free software licensing

    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
    омн
    -0.09
    лон
    -0.09
    ukan
    -0.09
    纯æ´ģ
    -0.09
    åĵij
    -0.08
    å«ģ
    -0.08
    å«ļ
    -0.08
    稿件
    -0.08
    illard
    -0.08
    æĸĹ
    -0.08
    POSITIVE LOGITS
    ä¸įä¸ĭ
    0.09
    ç¿»
    0.09
    mos
    0.09
    isphere
    0.09
     MPS
    0.08
    SKI
    0.08
    è¹Ħ
    0.08
     martin
    0.08
    强åĪ¶
    0.08
    å½¹
    0.08
    Activations Density 0.052%

    No Known Activations