© 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. 51366
    Prev
    Next
    INDEX
    Explanations

    yelling at, issue with, slam the

    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
    åIJĮå¿ĥ
    -0.10
    平衡
    -0.10
    å¯Ĥå¯ŀ
    -0.10
    害æĢķ
    -0.10
     wink
    -0.09
    æĥº
    -0.09
    æĢķ
    -0.09
     Sho
    -0.09
    ä»ĭç»įäºĨ
    -0.09
    æī¿
    -0.09
    POSITIVE LOGITS
    æĢĴ
    0.12
    æĦ¤æĢĴ
    0.12
    æģ¨ä¸įå¾Ĺ
    0.11
    æĴĤ
    0.11
    æĸ¥
    0.10
    æģ¨
    0.10
    å½ĵåľº
    0.10
    çĶŁæ°Ķ
    0.09
    è¯ħ
    0.09
    éªĤ
    0.09
    Activations Density 0.061%

    No Known Activations