© 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. 48869
    Prev
    Next
    INDEX
    Explanations

    injury and health problems

    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
    SCO
    -0.10
    å¯Ħ
    -0.10
    é¹ģ
    -0.09
    审åĪ¤
    -0.09
    æµģãĤĮ
    -0.09
    _utc
    -0.09
    æľ¬æĬ¥
    -0.09
    anging
    -0.09
    åĩĨå¤ĩ
    -0.09
    Fmt
    -0.08
    POSITIVE LOGITS
    çĶŁçĹħ
    0.10
    åģ¥åº·
    0.10
    ä¿Ŀåħ»
    0.10
    伤çĹħ
    0.09
     здоÑĢов
    0.09
    ä½ĵè´´
    0.09
    lam
    0.09
     здоÑĢовÑĮÑı
    0.09
    å¼ĢæĶ¯
    0.09
    åģ¥åº·çļĦ
    0.09
    Activations Density 0.024%

    No Known Activations