© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20372
    Prev
    Next
    INDEX
    Explanations

    performance times and records

    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
    祸
    -0.09
    ufs
    -0.09
    æĩĴ
    -0.09
    æīĵçĿĢ
    -0.09
     coun
    -0.09
    çIJ¼
    -0.09
    ignon
    -0.08
    é¦ĸåħĪæĺ¯
    -0.08
    BAL
    -0.08
    æĿı
    -0.08
    POSITIVE LOGITS
    纪å½ķ
    0.09
    åĪ³
    0.09
    æĪIJ绩
    0.09
    åħ¬ç¤º
    0.09
    æĪIJ绩åįķ
    0.09
    ç²ľ
    0.09
    åĭĥ
    0.08
    ä¼ĺå¼Ĥ
    0.08
     ÑįÑĤ
    0.08
     Bot
    0.08
    Activations Density 0.035%

    No Known Activations