© 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. 62737
    Prev
    Next
    INDEX
    Explanations

    email suffixes and names

    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
    éĩįå¤į
    -0.09
    itia
    -0.09
    mites
    -0.08
    诸
    -0.08
    äºĭåħ³
    -0.08
    archs
    -0.08
    Hooks
    -0.08
    æļijåģĩ
    -0.08
    ä»Ļ
    -0.08
    渴
    -0.08
    POSITIVE LOGITS
    æľ¬äºº
    0.10
    ä¸Ģ人
    0.09
    èıĮ
    0.09
    ä¸Ģ家人
    0.09
    亲
    0.09
    ä¸Ģ个人
    0.09
    æľ¬ç½ij
    0.08
    åĴĮä»ĸçļĦ
    0.08
    个人è§ĤçĤ¹
    0.08
     Enterprises
    0.08
    Activations Density 0.194%

    No Known Activations