© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7701
    Prev
    Next
    INDEX
    Explanations

    merge operation

    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
    emachine
    -0.10
    odel
    -0.10
     lưng
    -0.09
    æĢĢæĬ±
    -0.09
    æĻ¯åĮº
    -0.09
    ãģĦãĤĭ
    -0.08
     Virgin
    -0.08
    ored
    -0.08
    aire
    -0.08
    herence
    -0.08
    POSITIVE LOGITS
     дог
    0.10
    ä¸į代表
    0.09
    æĭĹ
    0.09
    -Benz
    0.09
    uvian
    0.08
    éĩįç»Ħ
    0.08
    -shop
    0.08
    flix
    0.08
    åͧ
    0.08
    .axis
    0.08
    Activations Density 0.039%

    No Known Activations