© 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. 17229
    Prev
    Next
    INDEX
    Explanations

    immune function and inflammation

    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
    .wrapper
    -0.09
    毡
    -0.08
    åħ¬å¹³
    -0.08
    åį·
    -0.08
     refill
    -0.08
    ä¿®åħ»
    -0.08
     warehouse
    -0.08
    ëĭ¹
    -0.08
    è®¤çľŁèIJ½å®ŀ
    -0.08
    æĮº
    -0.07
    POSITIVE LOGITS
    åħįçĸ«åĬĽ
    0.15
    åħįçĸ«
    0.12
    éĺ²åį«
    0.11
    é¼ĵèĪŀ
    0.11
    èĭ
    0.10
     immune
    0.10
    御
    0.10
    çĬĴ
    0.10
    éĺ²å¾¡
    0.09
    æī¶æĮģ
    0.09
    Activations Density 0.505%

    No Known Activations