© 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. 30035
    Prev
    Next
    INDEX
    Explanations

    renal organ function

    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
    éħļ
    -0.10
     horm
    -0.09
    å¥ī
    -0.09
    çļĦä¼ĺçĤ¹
    -0.09
    orsch
    -0.09
    abra
    -0.09
    éĺ²çĽĹ
    -0.09
    ä¹ĸ
    -0.09
    perature
    -0.09
    éĺĻ
    -0.09
    POSITIVE LOGITS
    åĻ¨å®ĺ
    0.13
    èĤ¾èĦı
    0.11
    ä¸į好
    0.11
     lungs
    0.11
     organ
    0.10
    èĤĿèĦı
    0.10
    acco
    0.10
     Singer
    0.09
     organs
    0.09
    åĬŁèĥ½
    0.09
    Activations Density 0.245%

    No Known Activations