© 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. 63680
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts

    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
    tees
    -0.09
    åĹĮ
    -0.08
    çļĦ羣å®ŀæĢ§
    -0.08
     Employ
    -0.08
     wearer
    -0.07
    èijĹ
    -0.07
    åıįæĺłåĩº
    -0.07
    -facebook
    -0.07
    åĮĹ京æŶéĹ´
    -0.07
    /ion
    -0.07
    POSITIVE LOGITS
    è¿ĩåħ³
    0.10
    ersive
    0.09
    ãģ£ãģĵ
    0.09
    éĬ®
    0.09
    oteric
    0.09
    ç¥Ł
    0.09
    ä¸ĩåįļ
    0.09
    mium
    0.09
     [âĢ¦]↵↵
    0.08
    å¨ģå°¼æĸ¯äºº
    0.08
    Activations Density 1.385%

    No Known Activations