© 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. 48058
    Prev
    Next
    INDEX
    Explanations

    complete a deal or transaction

    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
    YO
    -0.09
    asion
    -0.09
    ippers
    -0.09
    ennial
    -0.09
    agement
    -0.09
    è¿Ŀ
    -0.08
    æ¤ħåŃIJ
    -0.08
    ypad
    -0.08
    otic
    -0.08
    ibus
    -0.08
    POSITIVE LOGITS
    交æĺĵ
    0.15
     transactions
    0.14
     transaction
    0.12
     deal
    0.12
     deals
    0.12
     Deal
    0.11
    Transaction
    0.11
     Ñģдел
    0.10
    æľ¬æ¬¡äº¤æĺĵ
    0.10
    transaction
    0.10
    Activations Density 0.115%

    No Known Activations