© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58794
    Prev
    Next
    INDEX
    Explanations

    adverb endings

    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
    å¿ĥçĸ¼
    -0.10
    è®®äºĭ
    -0.10
    æ´¥
    -0.09
    åºĶæĶ¶
    -0.09
    HING
    -0.09
    åįĬ天
    -0.09
    ased
    -0.09
    æģ¤
    -0.09
    å·²äºİ
    -0.08
    éĤ£æł·çļĦ
    -0.08
    POSITIVE LOGITS
    ingly
    0.15
    ically
    0.14
    lessly
    0.14
    ently
    0.13
    ly
    0.13
    ìłģìľ¼ë¡ľ
    0.12
    owo
    0.12
    entially
    0.12
    ously
    0.12
    ily
    0.12
    Activations Density 0.366%

    No Known Activations