© 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. 35473
    Prev
    Next
    INDEX
    Explanations

    Internet Corporation for Assigned Names and Numbers

    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
    ä¸ĢåĪĨ
    -0.08
    ÑĢÑĥд
    -0.08
    åĬ¨äºº
    -0.08
    Dem
    -0.08
    orton
    -0.08
     Dem
    -0.08
    åIJĮæ¯Ķ
    -0.08
     comps
    -0.08
     Ces
    -0.08
     Dispatch
    -0.08
    POSITIVE LOGITS
    æĥľ
    0.10
    æīª
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    å·Ŀ
    0.09
    IT
    0.09
    och
    0.09
    éķľ
    0.09
     IT
    0.09
    Wildcard
    0.09
    çĺ¾
    0.09
    Activations Density 0.136%

    No Known Activations