© 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. 48157
    Prev
    Next
    INDEX
    Explanations

    place name suffixes

    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
    æ¼±
    -0.09
    ÑİÑĢ
    -0.09
    导åIJij
    -0.09
    inkle
    -0.09
    à¸Īร
    -0.08
    éŸ
    -0.08
    åįģä¹Ŀå±Ĭ
    -0.08
     barrage
    -0.08
    æįŀ
    -0.08
    åħļç»Ħ
    -0.08
    POSITIVE LOGITS
    enne
    0.10
    поÑĤ
    0.10
    ä¹ĥèĩ³
    0.09
    onic
    0.09
    åľ°åĮºçļĦ
    0.09
     topo
    0.09
    Trivia
    0.09
    ean
    0.08
    èµĦæºIJæķ´åIJĪ
    0.08
    é£İæĥħ
    0.08
    Activations Density 0.222%

    No Known Activations