© 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. 60770
    Prev
    Next
    INDEX
    Explanations

    bank account, savings, checking

    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
    -0.14
    keit
    -0.11
    åIJĦå¼ı
    -0.10
    åįĬå²Ľ
    -0.09
    _accounts
    -0.09
    /var
    -0.09
    ampton
    -0.09
    åģ¶
    -0.09
    æĪijçľĭ
    -0.09
    -quarters
    -0.09
    POSITIVE LOGITS
    sWith
    0.12
    ums
    0.10
    suming
    0.09
    пл
    0.09
    é
    0.09
    çĮ¿
    0.09
    ants
    0.09
    culate
    0.09
    mgr
    0.09
    تÙĩ
    0.09
    Activations Density 0.020%

    No Known Activations