© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1605
    Prev
    Next
    INDEX
    Explanations

    sales and outlets

    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
    agas
    -0.10
    縻
    -0.10
    æĤ¬æµ®
    -0.10
    ardy
    -0.09
    æĭĶ
    -0.09
    è¯ģçĽij
    -0.09
    æıIJä¾ĽåķĨ
    -0.09
    åĪĨæķ£
    -0.09
    äºĶåĪĨéĴŁ
    -0.09
    addField
    -0.09
    POSITIVE LOGITS
     sale
    0.10
     markup
    0.10
    æī«
    0.09
    throw
    0.09
     markdown
    0.09
     Markup
    0.09
    -sale
    0.09
     clearance
    0.09
     Goods
    0.09
    æĬĺæī£
    0.09
    Activations Density 0.091%

    No Known Activations