© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7130
    Prev
    Next
    INDEX
    Explanations

    intravenous fluids

    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
    ../
    -0.11
    halb
    -0.10
     اÙĦدÙĬÙĨ
    -0.09
    Çĥ
    -0.08
    bone
    -0.08
    ÑģÑĤи
    -0.08
    ©
    -0.08
    èµ·ä¼ı
    -0.08
    pai
    -0.08
     Balt
    -0.08
    POSITIVE LOGITS
    sWith
    0.10
    ä¸Ģ代
    0.10
    ../../../
    0.10
    ullo
    0.09
    hä
    0.09
    teen
    0.09
    ets
    0.09
    .freeze
    0.09
    è¿Ħ
    0.09
    æ¦ī
    0.09
    Activations Density 0.061%

    No Known Activations