© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8389
    Prev
    Next
    INDEX
    Explanations

    cardiac pulses, pressure support

    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
    iban
    -0.09
    _FORM
    -0.09
     Carr
    -0.08
    HandlerContext
    -0.08
    Forms
    -0.08
     Carnegie
    -0.08
    -par
    -0.08
    .dimension
    -0.08
    Dimension
    -0.08
    éĤ£åıª
    -0.08
    POSITIVE LOGITS
    çĸĹæ³ķ
    0.12
    ç¼¢
    0.10
    çĸĹæķĪ
    0.09
    çĻĤ
    0.09
    å¾ħéģĩ
    0.09
    è¾ĸ
    0.09
    ç»®
    0.09
    ç¾İçĻ½
    0.08
     auto
    0.08
    纶
    0.08
    Activations Density 0.157%

    No Known Activations