© 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. 31917
    Prev
    Next
    INDEX
    Explanations

    yard / yards

    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
    leh
    -0.10
    åģĥ
    -0.10
    lev
    -0.10
    æĪijä¸įæĥ³
    -0.10
    çľ¼çļ®
    -0.10
    esco
    -0.10
    å¸ĤåľºèIJ¥éĶĢ
    -0.09
    æīĭæİĮ
    -0.09
    ëĭ
    -0.09
    oft
    -0.09
    POSITIVE LOGITS
    igans
    0.10
    iful
    0.09
    onne
    0.09
    stick
    0.08
    amage
    0.08
    inality
    0.08
    acity
    0.08
    tog
    0.08
    ields
    0.08
    çĶŁäº§æĢ»åĢ¼
    0.08
    Activations Density 0.005%

    No Known Activations