© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60937
    Prev
    Next
    INDEX
    Explanations

    interest rates and currency

    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
    顼
    -0.10
    åĬŀ好
    -0.09
    æľįä»İ
    -0.09
    UTO
    -0.09
    åĨįä¹Ł
    -0.09
    人家
    -0.08
    åħ´èµ·
    -0.08
    æľį
    -0.08
    é½
    -0.08
    rena
    -0.08
    POSITIVE LOGITS
    egra
    0.09
    è°ĥæķ´
    0.09
    åºĬä¸Ĭ
    0.09
    次æķ°
    0.09
    ç®Ń
    0.09
    éĻį
    0.09
    endif
    0.09
    Advertisements
    0.08
    æĬĸ
    0.08
    akra
    0.08
    Activations Density 0.011%

    No Known Activations