© 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. 21211
    Prev
    Next
    INDEX
    Explanations

    size, dimensions, quantity

    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
    宿
    -0.09
    ä»ħ代表
    -0.09
    loth
    -0.09
    ä¸ĢèĦļ
    -0.08
    alie
    -0.08
    å²ij
    -0.08
    arkers
    -0.08
    æĿĥ
    -0.08
    wick
    -0.08
    ussion
    -0.08
    POSITIVE LOGITS
    è§Ħ模
    0.13
    size
    0.10
    SIZE
    0.10
    è¾ĥå°ı
    0.10
     sizes
    0.10
    è¦ı模
    0.10
     size
    0.10
    为ä¹ĭ
    0.09
    ãĤµãĤ¤ãĤº
    0.09
    çĦĬ
    0.09
    Activations Density 0.062%

    No Known Activations