© 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. 9445
    Prev
    Next
    INDEX
    Explanations

    medical treatment reduction

    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
    æīĢéľĢçļĦ
    -0.11
    OTH
    -0.10
    è¦ģç´§
    -0.10
    ä¼¼çļĦ
    -0.10
    éĴ¿
    -0.10
    èIJ½åħ¥
    -0.09
    æīĢéľĢè¦ģçļĦ
    -0.09
     desn
    -0.09
    LIK
    -0.09
    _eof
    -0.09
    POSITIVE LOGITS
    åĬłæĮģ
    0.11
     allegedly
    0.10
    带æĿ¥çļĦ
    0.10
    导èĩ´
    0.10
     vs
    0.09
    å¼ķèµ·çļĦ
    0.09
    ä¸İåIJ¦
    0.09
     supposedly
    0.09
    èĥĮ
    0.09
    åĬłä¹ĭ
    0.09
    Activations Density 1.166%

    No Known Activations