© 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. 38539
    Prev
    Next
    INDEX
    Explanations

    figures 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
    饿
    -0.10
    é£ĵ
    -0.10
    inde
    -0.09
    濯
    -0.09
    æĮ½
    -0.09
    alam
    -0.09
    ä¸įæĪIJ
    -0.09
    æµĬ
    -0.08
    åįĩåѦ
    -0.08
    æĪIJ为ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
    oure
    0.08
    ingo
    0.08
    omo
    0.07
    çĽĬ
    0.07
    ieur
    0.07
    loth
    0.07
    ç»Ĩç»Ĩ
    0.07
    _cleanup
    0.07
    _TRA
    0.07
    ä¸ĢæĬĬ
    0.07
    Activations Density 0.218%

    No Known Activations