© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8504
    Prev
    Next
    INDEX
    Explanations

    price and quantity

    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
     беÑģплаÑĤно
    -0.09
    noinspection
    -0.09
    åħīç͵
    -0.09
    squ
    -0.09
    ÑģÑĥд
    -0.08
    usi
    -0.08
    樾
    -0.08
    éĨ
    -0.08
    filesystem
    -0.08
    Ark
    -0.08
    POSITIVE LOGITS
    å»ī
    0.11
    约åIJĪ
    0.10
    å¾Ĺèµ·
    0.10
    å·¦åı³
    0.09
    allon
    0.08
    leans
    0.08
    æį¢æĿ¥
    0.08
    æ¿Ĥ
    0.08
    onga
    0.08
    说起
    0.08
    Activations Density 0.059%

    No Known Activations