© 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. 34717
    Prev
    Next
    INDEX
    Explanations

    homocysteine, lowering

    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
    带åĬ¨
    -0.09
    èĢĴ
    -0.08
    ãģĹãģĭ
    -0.08
     fract
    -0.08
    lung
    -0.08
    erer
    -0.08
    nof
    -0.08
     Cub
    -0.07
    å¦Ĥæľī
    -0.07
    å©
    -0.07
    POSITIVE LOGITS
    è±ļ
    0.11
    æĻºæħ§
    0.10
    åĬ¨æīĭ
    0.10
     Loud
    0.10
    ovich
    0.09
    è®®é¢ĺ
    0.09
     jÄĻzyk
    0.09
    ä¸Ģä½ĵ
    0.09
    cz
    0.09
    -sale
    0.09
    Activations Density 0.144%

    No Known Activations