© 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. 33768
    Prev
    Next
    INDEX
    Explanations

    Japanese surnames

    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
    หลวà¸ĩ
    -0.10
    å¾Īæ£Ĵ
    -0.09
    貸
    -0.08
    大åıĶ
    -0.08
     à¹Ĩ
    -0.08
    åķ¾
    -0.08
    uku
    -0.08
    ç°ĭ
    -0.08
    å¾Īæ¼Ĥ亮
    -0.08
    èĸľ
    -0.08
    POSITIVE LOGITS
    conti
    0.10
    ouv
    0.09
    acy
    0.09
    ental
    0.08
    athy
    0.08
    erras
    0.08
    бо
    0.08
    Connor
    0.08
    æŃ¤ä¸¾
    0.08
    edis
    0.08
    Activations Density 0.657%

    No Known Activations