© 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. 4339
    Prev
    Next
    INDEX
    Explanations

    loss of bone mass

    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
    纸ä¸Ĭ
    -0.10
    å¾Īå·®
    -0.10
    born
    -0.09
     Glasses
    -0.09
    ä¼ļä¸Ĭ
    -0.09
    iske
    -0.09
    å´Ľ
    -0.09
    sticks
    -0.09
    ئة
    -0.09
    KEEP
    -0.09
    POSITIVE LOGITS
    æ®Ĩ
    0.13
     due
    0.09
     dần
    0.08
    -Core
    0.08
    ãģ£ãģ
    0.08
    -too
    0.08
     depths
    0.08
    ä¸įæŃ¢
    0.08
    å¹ħ
    0.08
    主è¦ģåİŁåĽł
    0.08
    Activations Density 0.175%

    No Known Activations