© 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. 51589
    Prev
    Next
    INDEX
    Explanations

    mixing things together

    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
    esktop
    -0.09
    ered
    -0.09
    éĢłç¦ı
    -0.09
    åĴ¨
    -0.08
    è°
    -0.08
    纵
    -0.08
    eth
    -0.08
    åĻª
    -0.08
    icia
    -0.08
    guest
    -0.08
    POSITIVE LOGITS
    tures
    0.13
    tur
    0.10
    ango
    0.09
     Lund
    0.09
    åĮ¯
    0.09
    ä¸ĩ亿
    0.09
    åŁİ乡
    0.09
    øy
    0.09
    èݳ
    0.08
    OLOR
    0.08
    Activations Density 0.010%

    No Known Activations