© 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. 5366
    Prev
    Next
    INDEX
    Explanations

    quantities of money or users

    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
    æľīå¾Īå¤ļç§į
    -0.11
    è§Ħ模æľĢ大
    -0.11
    èµ°å¾Ĺ
    -0.10
    æĽ´èĥ½
    -0.10
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.10
    å¤ļå¤ļ
    -0.10
    é¢ĩ
    -0.10
    Ñĩив
    -0.10
    æ¯Ķè¾ĥå¤ļ
    -0.10
    ä¸į太好
    -0.10
    POSITIVE LOGITS
     thousands
    0.11
     millions
    0.10
     Millions
    0.10
     hundreds
    0.10
    åĩłåįģ
    0.09
    ieber
    0.09
     billions
    0.08
    Thousands
    0.08
    Hundreds
    0.08
     tens
    0.08
    Activations Density 0.080%

    No Known Activations