© 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. 10894
    Prev
    Next
    INDEX
    Explanations

    large company or organization

    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
    ä¸īæĸ¹
    -0.10
    ire
    -0.08
    æŀ¶
    -0.08
    ÑĢаб
    -0.08
    .nlm
    -0.08
    æĤ¬
    -0.08
    à¹ģà¸Ĺ
    -0.08
    ipa
    -0.08
    家éĩĮ
    -0.08
    ç»į
    -0.08
    POSITIVE LOGITS
    åºŀ大çļĦ
    0.20
    åºŀ大
    0.17
    è¿Ļä¹Ī大
    0.16
    è§Ħ模
    0.15
    é¾
    0.14
    è¦ı模
    0.12
     vast
    0.12
    å·¨åŀĭ
    0.12
    å®ı大
    0.11
    åºŀ
    0.11
    Activations Density 0.163%

    No Known Activations