© 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. 48461
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by way

    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
    没äºĭ
    -0.10
    æīŃ转
    -0.09
    ä¹°æĪ¿
    -0.09
    andro
    -0.09
    zia
    -0.09
    BSD
    -0.08
    bsd
    -0.08
    æĺ¯ä¸įä¼ļ
    -0.08
    ynos
    -0.08
    å¤ĩ
    -0.08
    POSITIVE LOGITS
    åīįå¾Ģ
    0.13
    å¥
    0.10
    ç³Ļ
    0.09
    éĢĶå¾Ħ
    0.09
    趣
    0.09
    ried
    0.09
    ãģ«åIJij
    0.09
    éĢļå¾Ģ
    0.09
    alto
    0.08
    åıŁ
    0.08
    Activations Density 0.036%

    No Known Activations