© 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. 10980
    Prev
    Next
    INDEX
    Explanations

    greeting or welcome

    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
    æ³ķå¾ĭ顾éĹ®
    -0.11
    åĴ«
    -0.11
     보기
    -0.10
    è´¨éĩı管çIJĨ
    -0.09
    ợ
    -0.09
    çIJĨ工大åѦ
    -0.09
    ikel
    -0.09
    /tiny
    -0.09
    æ¯ĶèµĽä¸Ń
    -0.09
    lector
    -0.09
    POSITIVE LOGITS
    è¿İæİ¥
    0.26
    è¿İ
    0.19
    欢è¿İ
    0.19
     welcome
    0.17
     welcoming
    0.17
     greet
    0.15
    Welcome
    0.15
     Welcome
    0.15
    welcome
    0.15
     greeted
    0.15
    Activations Density 0.053%

    No Known Activations