© 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. 9812
    Prev
    Next
    INDEX
    Explanations

    names ending in ie or ny

    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
    ally
    -0.10
    orde
    -0.09
    ëģĶ
    -0.09
    娣
    -0.09
     Salvador
    -0.09
    åİĿ
    -0.09
    触åıĬ
    -0.08
    .CodeAnalysis
    -0.08
    lington
    -0.08
    odium
    -0.08
    POSITIVE LOGITS
    mares
    0.11
    NING
    0.11
    ernals
    0.10
    mare
    0.10
    ../
    0.09
     lẽ
    0.09
    cial
    0.09
     Truyá»ģn
    0.09
    ķ
    0.08
    моÑĢ
    0.08
    Activations Density 0.025%

    No Known Activations