© 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. 1687
    Prev
    Next
    INDEX
    Explanations

    closing a sale or deal

    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
    æĭĪ
    -0.10
    导åIJij
    -0.09
    æ¿Ģåıij
    -0.09
    ynos
    -0.09
    èĢģ大
    -0.09
    icum
    -0.09
    äºĮç»´
    -0.08
     Variety
    -0.08
    RI
    -0.08
    æľīä¸ĢçĤ¹
    -0.08
    POSITIVE LOGITS
    áĥķ
    0.10
    åĪ³
    0.09
    骤
    0.09
    åį³ä½¿æĺ¯
    0.09
    æ´ĭèij±
    0.09
     hẹn
    0.09
    çļĦå¿ĥæĥħ
    0.09
    å§ĭç»Īä¿ĿæĮģ
    0.09
    èĵĦ
    0.09
    å±¥
    0.09
    Activations Density 0.224%

    No Known Activations