© 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. 63529
    Prev
    Next
    INDEX
    Explanations

    you + verb

    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
    èĭ¡
    -0.10
    æ·±å¤ľ
    -0.10
    åĵ¥ä¼¦æ¯Ķäºļ
    -0.10
    åĬĪ
    -0.10
    ä¸įèĩ³äºİ
    -0.10
     Câm
    -0.10
    å°ıå¿ĥ翼翼
    -0.09
    转载请
    -0.09
    åĮħåĮħ
    -0.09
     Hicks
    -0.09
    POSITIVE LOGITS
    eree
    0.09
    级以ä¸Ĭ
    0.09
     SD
    0.08
    hey
    0.08
    SD
    0.08
    飩
    0.08
    oras
    0.08
    çłº
    0.08
    ths
    0.08
    ä¸ŃåĽ½èģĶéĢļ
    0.08
    Activations Density 0.219%

    No Known Activations