© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51658
    Prev
    Next
    INDEX
    Explanations

    loan and borrowing

    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
    azes
    -0.09
    å±İ
    -0.09
    isis
    -0.09
    ç³ĸæŀľ
    -0.08
     Dum
    -0.08
    éĤ¸
    -0.08
    OMB
    -0.08
    xt
    -0.08
    ä¸Ģç«Ļ
    -0.08
    åłµ
    -0.08
    POSITIVE LOGITS
    åĢŁçĶ¨
    0.16
     borrow
    0.15
    åĢŁ
    0.15
    åij¨è½¬
    0.14
     borrowing
    0.12
     loan
    0.12
    borrow
    0.12
    .borrow
    0.11
    貸
    0.11
    åĢŁè´·
    0.11
    Activations Density 0.067%

    No Known Activations