© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7493
    Prev
    Next
    INDEX
    Explanations

    desserts and food items

    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
    åľ¨åľ°ä¸Ĭ
    -0.10
    .setUp
    -0.09
    ighth
    -0.09
    ItemImage
    -0.09
    FormItem
    -0.09
    åľ¨ç½ij绾ä¸Ĭ
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    çŀij
    -0.09
    åĪ©çī©
    -0.09
     Sanders
    -0.09
    POSITIVE LOGITS
    ç»Ŀ大éĥ¨åĪĨ
    0.09
    æ¸ħæĺİ
    0.08
    1
    0.08
    overs
    0.08
    wort
    0.08
    åĪĹ举
    0.08
    6
    0.08
    5
    0.08
    IER
    0.08
     Advisors
    0.08
    Activations Density 0.031%

    No Known Activations