© 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. 30835
    Prev
    Next
    INDEX
    Explanations

    emotional distress and patient demographics

    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
    stag
    -0.10
    åıĽ
    -0.10
    eyed
    -0.09
    æ¡Ģ
    -0.09
    amodel
    -0.09
    _FLASH
    -0.09
    åĥĩ
    -0.09
    åħħå®ŀ
    -0.09
     ÐłÐ°
    -0.09
    hawks
    -0.09
    POSITIVE LOGITS
    第ä¸ī人
    0.09
    çijķçĸµ
    0.09
    æİĴæ°´
    0.09
    人身
    0.09
    æĺİçŁ¥
    0.08
    æĢł
    0.08
    åħ±åĴĮåĽ½
    0.08
     neglig
    0.08
    å«ļ
    0.08
    ãĥ¡ãĤ¤ãĥ³
    0.08
    Activations Density 0.492%

    No Known Activations