© 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. 26656
    Prev
    Next
    INDEX
    Explanations

    aging and wrinkles

    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
     union
    -0.09
    æĪ¿æºIJ
    -0.09
    ä¸ĭ鼨
    -0.09
     ë°Ķ
    -0.09
    azi
    -0.09
    榫
    -0.09
    èĢį
    -0.08
     вкÑĥÑģ
    -0.08
    è´Ń票
    -0.08
    社ä¼ļåĮĸ
    -0.08
    POSITIVE LOGITS
    çļ±çº¹
    0.19
    è¡°èĢģ
    0.17
     aging
    0.15
    ¡°
    0.14
     wrinkles
    0.13
     age
    0.13
    é¢ľ
    0.12
    éĿ¢å®¹
    0.12
     Aging
    0.12
    å²ģæľĪ
    0.12
    Activations Density 0.080%

    No Known Activations