© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21430
    Prev
    Next
    INDEX
    Explanations

    success in procedures and outcomes

    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
    起身
    -0.10
    ä»£æĽ¿
    -0.09
    pac
    -0.09
    ascar
    -0.09
    æģ¢å¤į
    -0.08
     Lamb
    -0.08
    alley
    -0.08
    å¼Ģçİ©ç¬ij
    -0.08
    .pc
    -0.08
    _markup
    -0.08
    POSITIVE LOGITS
    æĪIJè´¥
    0.23
    çļĦæĪIJåĬŁ
    0.17
    æĪIJåĬŁçļĦ
    0.17
    æĪIJåĬŁ
    0.16
     success
    0.16
     ÑĥÑģпеÑħ
    0.15
     ÑĥÑģпеÑĪ
    0.13
    success
    0.13
    æĪIJåĬŁçİĩ
    0.13
    -success
    0.12
    Activations Density 0.053%

    No Known Activations