© 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. 29821
    Prev
    Next
    INDEX
    Explanations

    cardiovascular disease

    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
    ï¬ĥ
    -0.09
    åħ¥åºĵ
    -0.09
    åķ¬
    -0.09
    缮çļĦæĺ¯
    -0.08
    ivel
    -0.08
    ake
    -0.08
    è¡£æŁľ
    -0.08
    æ¯Ķè¾ĥ好
    -0.08
    ike
    -0.08
    -best
    -0.08
    POSITIVE LOGITS
    åįĹæµ·
    0.10
    æıª
    0.09
    èĩªæľī
    0.09
    âľĸ
    0.09
    人士
    0.09
    éľĢè¦ģçĶ¨
    0.09
    å²ĺ
    0.08
    åĹŁ
    0.08
    .vn
    0.08
     Muj
    0.08
    Activations Density 0.059%

    No Known Activations