© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38549
    Prev
    Next
    INDEX
    Explanations

    secret agents and operatives

    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
    æijĨæĶ¾
    -0.09
     Crossing
    -0.09
    头æĿ¡
    -0.08
    ÑĪин
    -0.08
    è·»
    -0.08
    ÑĢÑĥб
    -0.08
    è¶Ĭé«ĺ
    -0.08
     tire
    -0.08
    Pa
    -0.08
    rove
    -0.08
    POSITIVE LOGITS
    é£İäºij
    0.09
    atically
    0.09
    鸢
    0.09
    åĵ¡
    0.09
     kê
    0.09
    亢
    0.09
    å³Ļ
    0.09
    åIJįåįķ
    0.09
     Madden
    0.08
    entifier
    0.08
    Activations Density 0.012%

    No Known Activations