© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37268
    Prev
    Next
    INDEX
    Explanations

    MLB, Baseball, sports news

    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
    éĩįéĩį
    -0.09
    ми
    -0.09
    æĬ¼éĩij
    -0.09
    éľ¹
    -0.09
    hower
    -0.09
    åħļåĴĮæĶ¿åºľ
    -0.08
    CISION
    -0.08
    affles
    -0.08
    家乡
    -0.08
    ÙĤ
    -0.08
    POSITIVE LOGITS
    å¨ĺ
    0.10
    rium
    0.10
    itud
    0.09
    во
    0.09
    esimal
    0.09
    nox
    0.09
    éĢį
    0.08
    级
    0.08
     hei
    0.08
    俸
    0.08
    Activations Density 0.004%

    No Known Activations