© 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. 32560
    Prev
    Next
    INDEX
    Explanations

    premature or early timing

    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
    æ±¾
    -0.10
     Sac
    -0.09
    URA
    -0.09
    ç«ŀæĬĢ
    -0.09
    æĸĭ
    -0.08
    è·ĭ
    -0.08
    isel
    -0.08
    è¨Ĥ
    -0.08
    循çݯ
    -0.08
    循
    -0.08
    POSITIVE LOGITS
    æıIJåīį
    0.25
    æıIJæĹ©
    0.23
    æĹ©æĹ©
    0.19
     sỼm
    0.17
    æĹ©
    0.17
    æĹ©ãģĦ
    0.17
    æĹ©çĤ¹
    0.16
    å°½æĹ©
    0.14
    æĹ©åľ¨
    0.14
     premature
    0.14
    Activations Density 0.119%

    No Known Activations