© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11103
    Prev
    Next
    INDEX
    Explanations

    Bank, Airlines, Energy, Toyota, Hire

    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
    ä¸Ģä½ĵ
    -0.09
    深交
    -0.08
     def
    -0.08
    åij±
    -0.08
    å¼ķ导
    -0.08
    åħį责声æĺİ
    -0.08
    çļĦåķĨåĵģ
    -0.08
     seated
    -0.08
    ä¸Ģè¶Ł
    -0.08
    mere
    -0.08
    POSITIVE LOGITS
    çľĭæĿ¥
    0.11
    ä¸Ģçľ¼
    0.10
     anlaÅŁ
    0.09
    ık
    0.09
    mith
    0.09
    èĬ¦
    0.09
     добав
    0.08
     воÑģ
    0.08
    亿ä¸ĩ
    0.08
     conting
    0.08
    Activations Density 0.055%

    No Known Activations