© 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. 30567
    Prev
    Next
    INDEX
    Explanations

    itself, himself, themselves

    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
    ä½Ĩåľ¨
    -0.10
    ä¸į管
    -0.09
     ÑħозÑıйÑģÑĤв
    -0.08
    åĪĩåħ¥çĤ¹
    -0.08
    é£İåIJ¹
    -0.08
    ä½Ĩæĺ¯åľ¨
    -0.08
    éķIJ
    -0.08
    ä½Ĩçİ°åľ¨
    -0.08
    ç»Ħç»ĩçĶŁæ´»
    -0.08
     Lit
    -0.08
    POSITIVE LOGITS
    æľ¬èº«
    0.45
     itself
    0.41
    æľ¬èº«çļĦ
    0.41
    èĩªèº«
    0.40
    èĩªèº«çļĦ
    0.36
    æľ¬äºº
    0.35
     themselves
    0.31
    æľ¬èº«å°±
    0.30
    æľ¬èº«å°±æĺ¯
    0.29
     himself
    0.29
    Activations Density 0.128%

    No Known Activations