© 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. 20788
    Prev
    Next
    INDEX
    Explanations

    health

    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
    æĸĭ
    -0.09
    èµĸ
    -0.09
    èļ¤
    -0.09
    è½°
    -0.09
    gli
    -0.09
    修为
    -0.09
    æľªæĪIJå¹´
    -0.09
    าà¸ĩ
    -0.08
    æĮ¤
    -0.08
    ubb
    -0.08
    POSITIVE LOGITS
    ansson
    0.10
    liga
    0.09
    isas
    0.08
    èį
    0.08
    秫
    0.08
    æľīäºĨ
    0.08
    çħ
    0.08
    éĿ¢åīį
    0.08
    æĹĭå¾ĭ
    0.08
    ischen
    0.08
    Activations Density 0.033%

    No Known Activations