© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20955
    Prev
    Next
    INDEX
    Explanations

    attempting to

    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
    äºĭåĦ¿
    -0.09
    è¯Ŀ说
    -0.09
    isl
    -0.09
    éħįèµĦ
    -0.09
    ä»Ģä¹ĪæŶåĢĻ
    -0.08
     напÑĢавлен
    -0.08
    HEN
    -0.08
    ovable
    -0.08
    ãģ¡ãģ¯
    -0.08
    è¿Ļ次
    -0.08
    POSITIVE LOGITS
    à¹ĥà¸Ķ
    0.10
    amp
    0.10
    że
    0.10
    oid
    0.10
    ãĤ¤ãĥ«
    0.09
    æĺ¯æĪijçļĦ
    0.09
    ä½ķå¤Ħ
    0.09
    .dictionary
    0.08
     unl
    0.08
    inge
    0.08
    Activations Density 0.520%

    No Known Activations