© 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. 10937
    Prev
    Next
    INDEX
    Explanations

    cosmetic and plastic surgery

    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
    æīįçŁ¥éģĵ
    -0.10
    æ·±å¤Ħ
    -0.10
    峪
    -0.10
    èıģ
    -0.09
    åħ»èĤ²
    -0.09
    æĹĦ
    -0.09
    线ä¸ĭ
    -0.09
    ambre
    -0.09
    è¿Ļ个æĹ¶ä»£
    -0.09
    arge
    -0.09
    POSITIVE LOGITS
    åħ¼é¡¾
    0.09
    æŀģ
    0.09
    åij¼å£°
    0.08
    ç´¯
    0.08
    /be
    0.08
    åºŁ
    0.08
    ļ
    0.08
    大çģ«
    0.08
    temps
    0.08
     tid
    0.07
    Activations Density 0.028%

    No Known Activations