© 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. 57091
    Prev
    Next
    INDEX
    Explanations

    quickly followed by action

    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
    ware
    -0.10
    edly
    -0.09
    esa
    -0.09
    elijke
    -0.09
    vented
    -0.09
    à¹ģà¸Ķà¸ĩ
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.09
    ate
    -0.09
    çĦ¶æĺ¯
    -0.09
    å®ļäºĨ
    -0.09
    POSITIVE LOGITS
     enough
    0.12
     جدا
    0.10
    ее
    0.10
    åıĪ好
    0.10
    峡
    0.09
    Enough
    0.09
    æĪ³
    0.09
     chóng
    0.09
    EVER
    0.09
    姣
    0.09
    Activations Density 0.015%

    No Known Activations