© 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. 48974
    Prev
    Next
    INDEX
    Explanations

    price decrease/discount

    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
    åģĪ
    -0.12
    æĶ¶åıĹ
    -0.10
    羯
    -0.10
    IDO
    -0.10
    å´ĩå°ļ
    -0.09
    ç¥ŀåľ£
    -0.09
    骥
    -0.09
    æĴŃ
    -0.09
    оÑĩной
    -0.09
    aris
    -0.09
    POSITIVE LOGITS
    éĻįä»·
    0.12
    å»ī
    0.12
    éĻį
    0.11
    为äºĨ让
    0.10
    æī°ä¹±
    0.10
     discount
    0.10
    æĽ´ä½İ
    0.09
    ä¼ĺæĥł
    0.09
    为äºĨ
    0.08
    票价
    0.08
    Activations Density 0.190%

    No Known Activations