© 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. 52112
    Prev
    Next
    INDEX
    Explanations

    new, used, or opened items

    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
    çıĪ
    -0.09
    åľ¨çº¿åĴ¨è¯¢
    -0.08
    åģı离
    -0.08
    4
    -0.08
    gin
    -0.08
    BM
    -0.08
    çħ¨
    -0.08
    éŀ
    -0.08
    7
    -0.08
    èĢģæŧ
    -0.08
    POSITIVE LOGITS
    çĶŁç´ł
    0.10
    é¢ĸ
    0.10
    å¥Ĥ
    0.09
    檫
    0.09
    prm
    0.09
    athed
    0.09
    atory
    0.08
    GPC
    0.08
    è¿Ļå¼ł
    0.08
    æĸ°ä¸ī
    0.08
    Activations Density 0.019%

    No Known Activations