© 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. 59041
    Prev
    Next
    INDEX
    Explanations

    receipts and invoices

    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
    esium
    -0.10
    æĢ»èµĦ产
    -0.09
    éĩįéĩį
    -0.09
     Shed
    -0.09
    ç²¾èĭ±
    -0.09
    åħ«ä¸ª
    -0.08
    计åĪĴ
    -0.08
     наг
    -0.08
    å¿ĥè·³
    -0.08
     tapped
    -0.08
    POSITIVE LOGITS
    åıij票
    0.15
    票æį®
    0.13
     receipts
    0.12
    æĬ¬å¤´
    0.12
     receipt
    0.12
    åĩŃè¯ģ
    0.11
     Receipt
    0.11
    receipt
    0.10
    æŃ£è§Ħ
    0.10
     subrange
    0.09
    Activations Density 0.026%

    No Known Activations