© 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. 47772
    Prev
    Next
    INDEX
    Explanations

    severe medical conditions and vulnerability

    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
    é¢ĩ
    -0.12
    é¢ĩæľī
    -0.11
    é¢ĩ为
    -0.11
    èĬ±å¼Ģ
    -0.10
    æł¼å¤ĸ
    -0.09
    éķĴ
    -0.09
    .Raise
    -0.09
    tring
    -0.09
    æĶĢçĻ»
    -0.09
    å¾Īå¤ļæľĭåıĭ
    -0.09
    POSITIVE LOGITS
    以èĩ³äºİ
    0.11
    çĺ¦
    0.09
     lan
    0.08
    éĢı
    0.08
    æĢĿãģĦ
    0.08
     EMP
    0.08
    jab
    0.08
    REN
    0.08
    ä¸Ģæŀļ
    0.07
     unlikely
    0.07
    Activations Density 0.183%

    No Known Activations