© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37424
    Prev
    Next
    INDEX
    Explanations

    Christian principle

    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
    æľŁå¾ħ
    -0.09
    æģ¹
    -0.08
    åĽ«
    -0.08
     Communic
    -0.08
     sold
    -0.08
    çļĦåŃ¦ä¹ł
    -0.08
    ä¹ħ
    -0.08
     Territory
    -0.07
    å¹½
    -0.07
    æľŁçĽ¼
    -0.07
    POSITIVE LOGITS
    çĪ±å¿ĥ
    0.17
    æĹłç§ģ
    0.15
    伸åĩº
    0.14
    èī¯å¿ĥ
    0.14
    æķijåĬ©
    0.14
    人æĢ§
    0.14
    æĦŁåĬ¨
    0.13
    æħ·æħ¨
    0.13
    æķij人
    0.13
    å¥īçĮ®
    0.13
    Activations Density 0.081%

    No Known Activations