© 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. 29538
    Prev
    Next
    INDEX
    Explanations

    financial institutions and bank names

    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
    Negative Logits
    oby
    -0.10
    chemy
    -0.09
    andre
    -0.09
    URED
    -0.09
    ontology
    -0.09
    allon
    -0.09
    Ĥæķ°
    -0.08
     dish
    -0.08
    ãĤ³ãĥŁ
    -0.08
    IGNED
    -0.08
    POSITIVE LOGITS
    ruptcy
    0.15
    rupt
    0.11
    ers
    0.11
    esh
    0.11
    er
    0.10
    ster
    0.10
    aroo
    0.10
    olis
    0.10
    è¿Ļ个ä¸ĸçķĮ
    0.10
    и
    0.09
    Activations Density 0.015%

    No Known Activations