© 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. 19984
    Prev
    Next
    INDEX
    Explanations

    referring to oneself

    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
    åIJĪæ³ķæĿĥçĽĬ
    -0.09
    Ắ
    -0.08
    æľŁå¾ħ
    -0.08
    æ¤įæłij
    -0.08
    ä¸Ģ件äºĭ
    -0.08
    ijn
    -0.08
    æĥĶ
    -0.08
    å¤ĸæĿ¥
    -0.08
    å¤ĸåĮħ
    -0.08
    è¿Ļæľ¬ä¹¦
    -0.08
    POSITIVE LOGITS
    èĩªå·±
    0.23
    对èĩªå·±
    0.20
    ç»Ļèĩªå·±
    0.20
     Ñģебе
    0.20
    èĩªå·±çļĦ
    0.20
    èĩªèº«
    0.19
     ourselves
    0.19
    对èĩªå·±çļĦ
    0.19
    èĩªèº«çļĦ
    0.18
     oneself
    0.17
    Activations Density 0.075%

    No Known Activations