© 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. 39228
    Prev
    Next
    INDEX
    Explanations

    ischemia, hypoxia, hypothermia

    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
    çĪ±ç¾İ
    -0.10
    åĬ©
    -0.10
    éļıæŶéļı
    -0.09
     пÑĢоизведен
    -0.09
    xon
    -0.09
    enez
    -0.09
    ilon
    -0.09
    å®ļå±ħ
    -0.09
     unh
    -0.09
     TL
    -0.09
    POSITIVE LOGITS
    åĨ°
    0.12
    å¤įèĭı
    0.10
    richt
    0.10
    缺
    0.09
     Ramp
    0.09
    éĺĻ
    0.09
    æĮ½æķij
    0.09
    æīĩ
    0.09
    ä»Ļ
    0.08
     ice
    0.08
    Activations Density 0.385%

    No Known Activations