© 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. 11826
    Prev
    Next
    INDEX
    Explanations

    outsourcing and procurement services

    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¸ĩåįĥ
    -0.10
    èĢģå¸Ī们
    -0.09
    åĭĭç«ł
    -0.09
    æłĹ
    -0.09
    ssa
    -0.08
    ä¸ĸ人
    -0.08
    ÑĨов
    -0.08
    sson
    -0.08
    reur
    -0.08
    .DataContext
    -0.08
    POSITIVE LOGITS
     Ø¥ÙĦÙĬÙĩا
    0.09
    ä¹ħäºĨ
    0.09
    樵
    0.09
    nda
    0.08
    å¼ĢæĿ¥
    0.08
    ino
    0.08
    -friendly
    0.08
    第ä¸Ģéĥ¨
    0.08
    æ¼
    0.08
    æ·
    0.08
    Activations Density 0.006%

    No Known Activations