© 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. 2705
    Prev
    Next
    INDEX
    Explanations

    regional airline or recurring payment

    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
    unt
    -0.10
    _PG
    -0.10
    رÙĩ
    -0.09
    upy
    -0.09
    èĽ¾
    -0.08
    Warnings
    -0.08
    åĿĬ
    -0.08
    phalt
    -0.08
    irm
    -0.08
    ifest
    -0.08
    POSITIVE LOGITS
    好çľĭ
    0.10
    åĬłçĽŁ
    0.09
     clos
    0.09
    çļĦæľ¬è´¨
    0.09
    æ¢Ń
    0.09
    adier
    0.09
    棱
    0.09
    鸷
    0.09
    æīĪ
    0.09
    æľ¬è´¨
    0.09
    Activations Density 0.116%

    No Known Activations