© 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. 56123
    Prev
    Next
    INDEX
    Explanations

    version numbers and dates

    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
    é¦Ļ
    -0.09
    å¥Ķ
    -0.09
    èļĵ
    -0.09
    æĪĮ
    -0.09
    佬
    -0.09
    à¸Ħà¸ĩ
    -0.08
    åł°
    -0.08
    使åħ¶
    -0.08
    å®ļåIJij
    -0.08
    æĶ¿æĿĥ
    -0.08
    POSITIVE LOGITS
    æĪIJç«ĭ以æĿ¥
    0.11
    以æĿ¥
    0.10
    以ä¾Ĩ
    0.09
    ä¸įä¹ħ
    0.09
    æīĢ说çļĦ
    0.08
    -disabled
    0.08
     Membership
    0.08
     membership
    0.08
    Svg
    0.08
    åĬłåħ¥
    0.08
    Activations Density 0.026%

    No Known Activations