© 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. 27069
    Prev
    Next
    INDEX
    Explanations

    muscle denervation electromyography MRI findings

    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
    oyer
    -0.08
    oola
    -0.08
    çĭ¸
    -0.08
    éĢĭ
    -0.08
     dang
    -0.08
     amnesty
    -0.08
    inst
    -0.08
    swers
    -0.08
    æİ¢
    -0.08
    æĹ¥å¤ľ
    -0.07
    POSITIVE LOGITS
    ä¸ĢéŨ
    0.11
    æĤ¬
    0.11
    çĶµè´¹
    0.11
     paralyzed
    0.11
    çĶµåĬ¨
    0.10
    麻çĹ¹
    0.10
    adal
    0.10
    ä¸Ģé¦ĸ
    0.10
    ç¹¼
    0.09
    çĶ¨çĶµ
    0.09
    Activations Density 0.650%

    No Known Activations