© 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. 51482
    Prev
    Next
    INDEX
    Explanations

    verbs ending in "ing"

    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
     dazu
    -0.11
    erset
    -0.10
    roit
    -0.09
    æĹ¨åľ¨
    -0.09
    inaire
    -0.09
    icus
    -0.09
    efined
    -0.09
    ereg
    -0.09
    олж
    -0.09
    allas
    -0.09
    POSITIVE LOGITS
    åĵªæĢķ
    0.09
     ×ķ׾
    0.09
    åĿļå®ŀçļĦ
    0.08
    åĩĨå¤ĩå·¥ä½ľ
    0.08
    çī¢åĽº
    0.08
     future
    0.08
    èĵij
    0.08
     ×ķ׾×Ķ
    0.08
    ç»ĵå®ŀ
    0.07
    re
    0.07
    Activations Density 0.221%

    No Known Activations