© 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. 34261
    Prev
    Next
    INDEX
    Explanations

    annual events

    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
     Loose
    -0.10
    å¾ģæľį
    -0.09
    æĶ¾è¿ĩ
    -0.09
    å°ıäºĭ
    -0.09
    åħ¨éĿ¢åıijå±ķ
    -0.08
    容å¿į
    -0.08
    妮
    -0.08
    å¸ĤæķĻèĤ²
    -0.08
    erner
    -0.08
    ãģ»ãģĨ
    -0.08
    POSITIVE LOGITS
    æģĴ
    0.10
    åIJ¸
    0.10
     xuyên
    0.10
    å·²ä¹ħ
    0.09
    ä¾ĭè¡Į
    0.09
    Orm
    0.09
    æѤ类
    0.09
    æ²½
    0.08
    mente
    0.08
     Brigham
    0.08
    Activations Density 0.014%

    No Known Activations