© 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. 49989
    Prev
    Next
    INDEX
    Explanations

    skin conditions and arts

    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
    moz
    -0.09
    APE
    -0.09
    åİħ
    -0.09
    tail
    -0.08
     miscellaneous
    -0.08
    룴
    -0.08
    ç»ŀ
    -0.08
    顶
    -0.08
    è¹ī
    -0.08
    å°ıåѦçĶŁ
    -0.08
    POSITIVE LOGITS
    ishes
    0.10
    çijķçĸµ
    0.09
    çĭ¸
    0.08
    æĸĩç§ij
    0.08
    æŀ
    0.08
    æľªç»ıæİĪæĿĥ
    0.08
     dia
    0.08
    çĸ®
    0.08
    ãĤĦãģĻ
    0.08
    ective
    0.08
    Activations Density 0.031%

    No Known Activations