© 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. 17053
    Prev
    Next
    INDEX
    Explanations

    money, finance, transactions

    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
    ively
    -0.13
     пÑĢава
    -0.10
    mdl
    -0.09
    icles
    -0.09
    路桥
    -0.09
     ÑģовеÑĢÑĪен
    -0.09
    sid
    -0.09
    -mounted
    -0.09
    åħ¶æīĢ
    -0.08
    phans
    -0.08
    POSITIVE LOGITS
     laundering
    0.11
    è±¹
    0.10
    alem
    0.09
    è¢ĭåŃIJ
    0.09
     tá»ĩ
    0.09
    èĬ¥
    0.09
    licit
    0.09
    dance
    0.09
    à¸ķรา
    0.09
    rou
    0.08
    Activations Density 0.018%

    No Known Activations