© 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. 1654
    Prev
    Next
    INDEX
    Explanations

    wholesale and retail businesses

    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
    åŁºéĩij管çIJĨ
    -0.09
    æĿ°åĩº
    -0.08
    è¾¹ç¼ĺ
    -0.08
    æ²¹çĶ°
    -0.08
    èĩªæĦ¿
    -0.08
    orm
    -0.08
    åĪĪ
    -0.08
    orz
    -0.08
    imes
    -0.08
    éĺµèIJ¥
    -0.08
    POSITIVE LOGITS
    鼶åĶ®
    0.17
    åĪĨéĶĢ
    0.14
    æī¹åıij
    0.14
     retail
    0.14
    鼶åĶ®åķĨ
    0.11
    Retail
    0.11
     wholesale
    0.10
    缴éĶĢ
    0.10
     Retail
    0.10
    à¸Īำหà¸Ļ
    0.10
    Activations Density 0.080%

    No Known Activations