© 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. 7985
    Prev
    Next
    INDEX
    Explanations

    oil companies and service providers

    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
    åĵģä½į
    -0.10
    æĪij以为
    -0.10
    Monkey
    -0.10
    æ¯Ĥ
    -0.10
    åIJĨ
    -0.10
    éĮ¾
    -0.09
    èĥ¡åIJĮ
    -0.09
    èĢľ
    -0.09
    lotte
    -0.08
    æĪij们认为
    -0.08
    POSITIVE LOGITS
    جاÙĨ
    0.10
    çŀŃ
    0.09
    rey
    0.08
    4
    0.08
    3
    0.08
    ships
    0.08
    urs
    0.08
    ÑĢог
    0.08
    7
    0.08
    2
    0.08
    Activations Density 0.001%

    No Known Activations