© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37448
    Prev
    Next
    INDEX
    Explanations

    you're

    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
    ä»ĸèĩªå·±
    -0.13
    æĪijèĩªå·±
    -0.12
     themselves
    -0.11
    åijĬè¯īä½ł
    -0.11
    æĪij们åı¯ä»¥
    -0.09
    æĪij们åºĶ该
    -0.09
    edom
    -0.09
    еÑģÑĤÑĮ
    -0.09
    .Dom
    -0.09
    ÑĨÑĥ
    -0.09
    POSITIVE LOGITS
     yourself
    0.21
     yourselves
    0.17
     bè
    0.17
     Yourself
    0.15
    åĽłä¸ºä½ł
    0.13
    're
    0.13
    nger
    0.13
     עצ×ŀ
    0.12
     guys
    0.12
    ä½łèĩªå·±
    0.12
    Activations Density 1.619%

    No Known Activations