© 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. 22990
    Prev
    Next
    INDEX
    Explanations

    allows allowing

    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
    uria
    -0.10
    åļ¼
    -0.09
    åĽ½ç±į
    -0.09
    è¯ģå®ŀ
    -0.09
    æĪĸå°Ĩ
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    _ARCH
    -0.09
    å°ĨåĨĽ
    -0.08
    ä¸ĵä¸ļåĮĸ
    -0.08
    à¸Ĭà¸Ļ
    -0.08
    POSITIVE LOGITS
    便äºİ
    0.13
    åĪ©äºİ
    0.10
    æĺĵäºİ
    0.09
    æĽ´å®¹æĺĵ
    0.09
    å®īæħ°
    0.09
    æĬļ
    0.09
    容纳
    0.09
    人们
    0.08
    æľīåĪ©äºİ
    0.08
    å¾Īå¤ļäºĭæĥħ
    0.08
    Activations Density 0.190%

    No Known Activations