© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49752
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or concern

    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
    åĹ£
    -0.09
    äºĮ代
    -0.09
    è¿ĩ渡
    -0.08
     Mang
    -0.08
    iso
    -0.08
    é¢Ķ
    -0.08
    ÑĤай
    -0.08
    åŃķ
    -0.08
    5
    -0.08
     fuck
    -0.08
    POSITIVE LOGITS
    åĺ²ç¬ij
    0.11
    å¹³åĩ¡
    0.11
    éģIJ
    0.10
    æĮ«æĬĺ
    0.10
    æĭ¼æIJı
    0.09
    å°±æĺ¯è¿Ļæł·
    0.09
    ä¸ĢåĪ»
    0.09
    .sym
    0.09
    éĤ£æł·
    0.09
    éĤ£æł·çļĦ
    0.09
    Activations Density 0.332%

    No Known Activations