© 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. 36180
    Prev
    Next
    INDEX
    Explanations

    reflective pronouns

    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
    泺
    -0.10
    .swap
    -0.10
    åºĦ严
    -0.10
    忧
    -0.10
    ä¸įçĶĺ
    -0.10
    åħ¬å¼Ģ课
    -0.09
    arest
    -0.09
     rop
    -0.09
    æľīçĽĬ
    -0.09
    éªĮ
    -0.09
    POSITIVE LOGITS
    ä½łèĩªå·±
    0.23
    à¹Ģà¸Ńà¸ĩ
    0.22
    èĩªå·±
    0.21
     ourselves
    0.21
     yourself
    0.20
    æĪijèĩªå·±
    0.20
     oneself
    0.19
    èĩªèº«
    0.18
    ä»ĸèĩªå·±
    0.18
     myself
    0.18
    Activations Density 0.092%

    No Known Activations