© 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. 51886
    Prev
    Next
    INDEX
    Explanations

    magazine or journal publication

    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
    ä¸įå¼Ģ
    -0.10
    bread
    -0.10
    icz
    -0.10
    éħįèµĦ
    -0.09
    åħ¨å¥Ĺ
    -0.09
    çħ¦
    -0.09
    emens
    -0.09
    oli
    -0.08
    olate
    -0.08
    çıª
    -0.08
    POSITIVE LOGITS
    (crate
    0.12
    ary
    0.12
    spath
    0.10
    suming
    0.09
    ity
    0.09
    æĴĴ
    0.09
    aries
    0.09
    ãģĦãģŁãĤī
    0.09
    ETO
    0.09
    æ´½
    0.09
    Activations Density 0.013%

    No Known Activations