© 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. 48946
    Prev
    Next
    INDEX
    Explanations

    if else statements

    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
    èĻİ
    -0.10
     pur
    -0.09
     dispens
    -0.08
     пед
    -0.08
     smear
    -0.08
     defaultMessage
    -0.08
    olem
    -0.08
    æģ¨ä¸įå¾Ĺ
    -0.08
    (vo
    -0.08
    æī°
    -0.08
    POSITIVE LOGITS
    éĻĪè¿°
    0.12
    æĿ¡ä»¶
    0.11
     Stmt
    0.11
    åīįæıIJæĺ¯
    0.11
     conditional
    0.11
     ÑĥÑģлов
    0.11
    è¯Ńæ°Ķ
    0.10
    åĪĨæĶ¯
    0.10
    æ¢Ŀ件
    0.10
    åīįæıIJ
    0.10
    Activations Density 0.169%

    No Known Activations