© 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. 56779
    Prev
    Next
    INDEX
    Explanations

    hyperglycemia and blood pressure

    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
    æį·
    -0.09
     Garn
    -0.08
    STEM
    -0.08
    å¾Īæ¸ħæ¥ļ
    -0.08
    æ¸ħé¦Ļ
    -0.08
    ä¸ĢæŃ¥
    -0.08
    hol
    -0.08
    avors
    -0.08
    ç´§åĩij
    -0.08
    翼
    -0.08
    POSITIVE LOGITS
    è¡Ģåİĭ
    0.11
     ÑģкаÑĩ
    0.10
    å½Ĵå±ŀäºİ
    0.09
    è¯Ŀ
    0.09
    çį¬
    0.09
    å°¹
    0.09
    è¿ĩ大
    0.09
     CONTRIBUTORS
    0.08
    ost
    0.08
    çĽĺæ´»
    0.08
    Activations Density 0.086%

    No Known Activations