© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37407
    Prev
    Next
    INDEX
    Explanations

    wage growth, annual growth

    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
    umar
    -0.09
    ä¿¡
    -0.09
    stk
    -0.09
    .connector
    -0.09
    å¾ģæľį
    -0.09
    æĶ¶åĽŀ
    -0.09
    bury
    -0.08
    éĻª
    -0.08
    ilig
    -0.08
    eature
    -0.08
    POSITIVE LOGITS
    å·¥ä¼ļ
    0.09
    DRV
    0.09
    enticate
    0.09
    åĵº
    0.09
    Drv
    0.09
    åĿļ飧
    0.09
    çĥŃè®®
    0.08
    çļĦ妻åŃIJ
    0.08
    æĸ°éĹ»åıijå¸ĥ
    0.08
    èĩªåĬ©
    0.08
    Activations Density 0.034%

    No Known Activations