© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21932
    Prev
    Next
    INDEX
    Explanations

    stratified

    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
    ç¬ı
    -0.09
    æł¼æŀĹ
    -0.09
    otted
    -0.09
    讼
    -0.09
    饴
    -0.09
    çļĩ家
    -0.08
    趸
    -0.08
     thuyết
    -0.08
    æģ½
    -0.08
    á»ĩ
    -0.08
    POSITIVE LOGITS
    bred
    0.09
    dating
    0.09
    ulent
    0.09
    ë°¥
    0.08
    ernal
    0.08
    ол
    0.08
    è°ģèĥ½
    0.08
    pheric
    0.08
    edic
    0.08
    -minded
    0.08
    Activations Density 0.008%

    No Known Activations