© 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. 3981
    Prev
    Next
    INDEX
    Explanations

    redistribute it and/or modify

    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
    èªĵ
    -0.10
     Perry
    -0.09
    OnClick
    -0.09
     clicking
    -0.09
    çĩļ
    -0.08
    	types
    -0.08
    çĭ¬å®¶
    -0.08
    çĺ¦èº«
    -0.08
    æ´¸
    -0.08
    å¤ĸåĮħ
    -0.08
    POSITIVE LOGITS
    çĪµ
    0.10
    对åħ¶è¿Ľè¡Į
    0.10
    å®£ä¼łæķĻèĤ²
    0.09
    æĶ¹ç¼ĸ
    0.09
    AZE
    0.09
    æĹłåģ¿
    0.09
    lus
    0.08
    تب
    0.08
    -any
    0.08
    ä»İä¸Ń
    0.08
    Activations Density 0.186%

    No Known Activations