© 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. 58671
    Prev
    Next
    INDEX
    Explanations

    investor relations, management, evangelist, public affairs

    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
    оÑĩно
    -0.09
    ç½¾
    -0.09
    .bn
    -0.09
    åĴĢ
    -0.08
    é¢Ĩ导èĢħ
    -0.08
    ä¸Ńåħ±ä¸Ń央
    -0.08
     impr
    -0.08
    wich
    -0.08
    æīŃ
    -0.08
     Leaders
    -0.08
    POSITIVE LOGITS
     пÑĢием
    0.11
    èģĶ绾
    0.11
    å®£ä¼ł
    0.10
    å®£ä¼łæ´»åĬ¨
    0.10
    åĩ½
    0.10
    æ´½
    0.10
    æݨ广
    0.10
    клад
    0.09
     outreach
    0.09
    ä¹ħäºĨ
    0.09
    Activations Density 0.065%

    No Known Activations