© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    renal failure

    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
    åł
    -0.09
    表çĻ½
    -0.09
    æĪı
    -0.09
    é¦ĸ缸
    -0.08
    à¸Ľà¸£à¸°à¸ģ
    -0.08
    èī¯å¿ĥ
    -0.08
    timeofday
    -0.08
    olf
    -0.08
    ä¸įå®Į
    -0.08
     ноÑĩ
    -0.08
    POSITIVE LOGITS
    åĵĢ
    0.09
    夷
    0.09
    ваÑĤ
    0.09
    ply
    0.09
    ä¸ľæµ·
    0.09
     Ventura
    0.09
    æµ£
    0.08
    лÑİб
    0.08
    udden
    0.08
     Sad
    0.08
    Activations Density 0.131%

    No Known Activations