© 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. 54921
    Prev
    Next
    INDEX
    Explanations

    credit, loan, borrow, trade

    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
    _HAL
    -0.09
    çīĴ
    -0.09
    æįIJ
    -0.09
    ä¸įç»ıæĦı
    -0.09
    é¡¿
    -0.09
    geh
    -0.09
    èģĬ
    -0.08
    wow
    -0.08
    æĪ´çĿĢ
    -0.08
    éłĵ
    -0.08
    POSITIVE LOGITS
    èµĬ
    0.17
     borrow
    0.15
    贷款
    0.15
    åĢŁæ¬¾
    0.15
    æ¬ł
    0.14
     borrowing
    0.14
    åĪĨæľŁ
    0.14
    åĢŁéĴ±
    0.14
     borrowed
    0.14
    borrow
    0.14
    Activations Density 0.070%

    No Known Activations