© 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. 38904
    Prev
    Next
    INDEX
    Explanations

    intermediary, mediate, broker, middleman

    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
    adin
    -0.09
    çŃĶ
    -0.09
    éľĨ
    -0.08
    ä¾Ŀ
    -0.08
     ÙĪاÙĦع
    -0.08
    åŃ¥
    -0.08
    å·¡èĪª
    -0.08
    OSE
    -0.08
    æĹ¶æľŁ
    -0.08
    åĩºçĤī
    -0.08
    POSITIVE LOGITS
    ä¸Ńä»ĭ
    0.15
    ä¸ŃéĹ´
    0.12
    ä¸Ńä»ĭæľºæŀĦ
    0.10
     intermedi
    0.10
    otime
    0.10
    éĩįéĩį
    0.09
     intermediary
    0.09
    éĢļéģĵ
    0.09
    è·ĭ
    0.09
    éģįå¸ĥ
    0.09
    Activations Density 0.023%

    No Known Activations