© 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. 30611
    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
    å±ĭåŃIJ
    -0.09
     Redistributions
    -0.09
    nt
    -0.09
    anda
    -0.08
    满满
    -0.08
    满满çļĦ
    -0.08
    åŀ®
    -0.08
    mit
    -0.08
    éķľåŃIJ
    -0.08
    äºİæĺ¯
    -0.08
    POSITIVE LOGITS
    vier
    0.12
    forth
    0.10
    说æĺ¯
    0.09
    iros
    0.09
    ä»Ģä¹Īäºĭ
    0.09
    ãĢħ
    0.09
    åı¦æľī
    0.09
    vely
    0.09
    ä¸įçĦ¶
    0.09
     кÑĥда
    0.09
    Activations Density 0.018%

    No Known Activations