© 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. 61442
    Prev
    Next
    INDEX
    Explanations

    self-reflection prompts

    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
    ominated
    -0.09
     вообÑīе
    -0.09
    oufl
    -0.09
     ÙĨÙĬÙĪز
    -0.08
    æķ´ä½ĵ
    -0.08
    æ³»
    -0.08
    isser
    -0.08
     INDIRECT
    -0.08
    Divider
    -0.08
    ounced
    -0.08
    POSITIVE LOGITS
    å¤ļç§įå½¢å¼ı
    0.11
    å¾Īå¤ļäºĭæĥħ
    0.10
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    屿
    0.09
    è¿Ļ段
    0.09
     Vand
    0.09
    ç»
    0.08
    ç¬ĥ
    0.08
    å©·
    0.08
    Activations Density 0.008%

    No Known Activations