© 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. 30093
    Prev
    Next
    INDEX
    Explanations

    if conditional statement

    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
    éĽªèĬ±
    -0.11
    çĬĦ
    -0.10
    æĸĩ书
    -0.09
    çĮĹ
    -0.09
    èªĵ
    -0.09
    èµĦäº§è´ŁåĢº
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
    å¸Ĥä¸Ńå¿ĥ
    -0.08
    绯
    -0.08
    SPACE
    -0.08
    POSITIVE LOGITS
    .mainloop
    0.10
    кла
    0.09
    ä¸Ģæł·
    0.09
    AMES
    0.09
    éĽģ
    0.09
    iske
    0.09
    èīĩ
    0.09
    leys
    0.09
    æıIJè®®
    0.09
    ches
    0.09
    Activations Density 0.199%

    No Known Activations