© 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. 51643
    Prev
    Next
    INDEX
    Explanations

    suffixes like -like, -ish, -style, -ian

    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
    å¾Ī好
    -0.11
    chy
    -0.10
    ainers
    -0.09
     McCart
    -0.09
    诸èijĽ
    -0.08
    说äºĨ
    -0.08
    Ñįн
    -0.08
    è¿ĺ好
    -0.08
    èĩªçĶ±è´¸æĺĵ
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    POSITIVE LOGITS
    åºł
    0.10
    utz
    0.09
    åĪĨå±Ģ
    0.09
    å¼ķè¿Ľ
    0.08
    ichi
    0.08
     broad
    0.08
    éģµ
    0.08
    æĭĽ
    0.08
    iel
    0.08
    ycz
    0.08
    Activations Density 0.045%

    No Known Activations