© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37969
    Prev
    Next
    INDEX
    Explanations

    most [adjective describing eminence]

    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
    åĨħçļĦ
    -0.09
    /th
    -0.08
    rosse
    -0.08
    oni
    -0.08
    atz
    -0.08
    AZ
    -0.08
    大åħ¨
    -0.08
    RES
    -0.08
    ами
    -0.08
    onth
    -0.07
    POSITIVE LOGITS
     thing
    0.12
    æѤ类
    0.11
     way
    0.10
    å®ŀæĸ½æĦıè§ģ
    0.10
    ä¸Ģç«Ļ
    0.10
    ä»»ä½ķå½¢å¼ı
    0.10
    åIJĮç±»
    0.09
    -ever
    0.09
    åħ¶æīĢ
    0.09
     Ðļи
    0.09
    Activations Density 0.107%

    No Known Activations