© 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. 49655
    Prev
    Next
    INDEX
    Explanations

    trade associations and chambers

    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
    ä¸Ģ款
    -0.09
    æ³»
    -0.08
    æĺ¯ä¸Ģ款
    -0.08
    çĶŁäº§è½¦éĹ´
    -0.08
    ç¾İ好çĶŁæ´»
    -0.08
    èĬ½
    -0.08
    ç½ijçĤ¹
    -0.08
    赶
    -0.08
    picker
    -0.08
    PAD
    -0.08
    POSITIVE LOGITS
    åįıä¼ļ
    0.12
    åķĨä¼ļ
    0.12
    è¡Įä¸ļåįıä¼ļ
    0.12
    åįıä¼ļä¼ļéķ¿
    0.11
    è¡Įä¸ļçļĦ
    0.11
    æĸ°çļĦä¸Ģ
    0.10
     Chambers
    0.10
    åī¯ä¼ļéķ¿
    0.10
     lobbyist
    0.10
    ä¼ļåijĺ
    0.10
    Activations Density 0.138%

    No Known Activations