© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50718
    Prev
    Next
    INDEX
    Explanations

    bone density and osteoporosis

    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
    spa
    -0.09
     win
    -0.09
     purge
    -0.09
     اÙĦÙĨÙĤ
    -0.09
    icals
    -0.09
    æ¶İ
    -0.08
    管çIJĨéĥ¨éŨ
    -0.08
    åł°
    -0.08
    è·Łä¸įä¸Ĭ
    -0.08
    åĢ¾
    -0.08
    POSITIVE LOGITS
    骨
    0.13
     bone
    0.12
    oste
    0.11
    骨骼
    0.11
    bone
    0.11
     Bone
    0.11
    骨头
    0.10
     oste
    0.10
    Bone
    0.10
     Bones
    0.10
    Activations Density 0.102%

    No Known Activations