© 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. 7044
    Prev
    Next
    INDEX
    Explanations

    sequential connectors

    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¸įèĩ³äºİ
    -0.10
     поможеÑĤ
    -0.09
    åħĪè¡Į
    -0.09
    çĪ¶åŃIJ
    -0.09
    iona
    -0.09
    ç»ıèIJ¥çIJĨ念
    -0.09
    ä¹Łæĺ¯å¾Ī
    -0.08
    æĽ´å¥½åľ°
    -0.08
    åįģ大
    -0.08
    logan
    -0.08
    POSITIVE LOGITS
     finally
    0.19
    æľĢåIJİ
    0.15
     Lastly
    0.15
    Lastly
    0.14
     third
    0.14
    finally
    0.13
    第ä¸ī个
    0.13
     Finally
    0.13
     ÑĤÑĢеÑĤÑĮ
    0.13
    Finally
    0.13
    Activations Density 0.213%

    No Known Activations