© 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. 5623
    Prev
    Next
    INDEX
    Explanations

    makeup and cosmetic terms

    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
    幸
    -0.10
    steam
    -0.09
    plural
    -0.09
    åīĶ
    -0.09
    å£ģ
    -0.09
    翼
    -0.09
    orate
    -0.09
    å´İ
    -0.09
    å¾½
    -0.09
    ife
    -0.09
    POSITIVE LOGITS
    ç§
    0.09
    庶
    0.09
    åĮĸ解
    0.08
    ä¸Ńå°ıåŀĭ
    0.08
     Dob
    0.08
    å°ijéĩı
    0.08
    çŁ¿çī©
    0.08
    editor
    0.08
    åĨħåĪĨæ³Į
    0.08
    ä»£æĽ¿
    0.08
    Activations Density 0.027%

    No Known Activations