© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36840
    Prev
    Next
    INDEX
    Explanations

    relief of pain or symptoms

    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
    YST
    -0.10
    æİ°
    -0.10
    çĶ¨åĬĽ
    -0.09
    æķŀå¼Ģ
    -0.09
    æįŁåĿı
    -0.09
    éĢı
    -0.09
    硼
    -0.08
    vvm
    -0.08
    åĤ»
    -0.08
    ä¸Ģé¡¿
    -0.08
    POSITIVE LOGITS
    åĩıè½»
    0.13
    åĽ°æī°
    0.11
    ç¼ĵ解
    0.10
    çĸ¼çĹĽ
    0.09
    çĹĽèĭ¦
    0.09
    å®īå®ģ
    0.09
     pain
    0.09
    æµĵ
    0.09
     relief
    0.08
    è¡Įèµ°
    0.08
    Activations Density 0.186%

    No Known Activations