© 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. 22055
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    urity
    -0.10
     ngá»Ļ
    -0.09
    atoria
    -0.09
    äºĨä¸Ģåı£
    -0.09
    æ¯ĴæĢ§
    -0.09
    endet
    -0.08
    missible
    -0.08
    hower
    -0.08
    гаÑĢ
    -0.08
    åĴĤ
    -0.08
    POSITIVE LOGITS
    åħ³èĬĤ
    0.15
    çĸ¼çĹĽ
    0.15
    çĸ¼
    0.15
    çĹĽãģ¿
    0.12
    èĤĮèĤī
    0.12
    康å¤į
    0.12
    æ¤İ
    0.12
     Mus
    0.11
    åĬĽåѦ
    0.11
     Pain
    0.11
    Activations Density 0.503%

    No Known Activations