© 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. 8131
    Prev
    Next
    INDEX
    Explanations

    the or on followed by article

    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
    akers
    -0.10
    å±Ĥåĩº
    -0.10
    velle
    -0.10
    ÑıÑģ
    -0.09
    ái
    -0.09
    utow
    -0.09
    пал
    -0.09
    еÑĩа
    -0.09
    alking
    -0.09
    ination
    -0.09
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.09
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
     <![
    0.08
    ned
    0.08
    ield
    0.08
    è°Ľ
    0.08
    loid
    0.08
    工夫
    0.08
     a
    0.08
    lad
    0.08
    Activations Density 0.165%

    No Known Activations