© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7405
    Prev
    Next
    INDEX
    Explanations

    loan and mortgage terms

    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
    çīĴ
    -0.12
    ç¿Ĵæħ£
    -0.09
    @qq
    -0.09
    èķĥ
    -0.09
    æĥ¯
    -0.09
    æħ£
    -0.09
    çķª
    -0.08
    ä¹łæĥ¯
    -0.08
    çĴĢ
    -0.08
    ereal
    -0.08
    POSITIVE LOGITS
    贷款
    0.16
     loans
    0.16
     loan
    0.13
    _loan
    0.12
    åĢŁæ¬¾
    0.11
    è´·
    0.11
     Loans
    0.11
    .obtain
    0.10
    貸款
    0.10
     préstamo
    0.10
    Activations Density 0.035%

    No Known Activations