© 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. 51664
    Prev
    Next
    INDEX
    Explanations

    health

    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
    1
    -0.09
    9
    -0.08
    缩çŁŃ
    -0.08
    3
    -0.08
    溺
    -0.08
     coolest
    -0.08
    æ¸Ĺ
    -0.08
    éªĩ
    -0.08
    0
    -0.07
    7
    -0.07
    POSITIVE LOGITS
    åģ¥åº·
    0.23
     health
    0.21
    身ä½ĵåģ¥åº·
    0.20
    åģ¥åº·çļĦ
    0.19
    health
    0.19
     здоÑĢов
    0.18
     здоÑĢовÑĮÑı
    0.18
    身å¿ĥåģ¥åº·
    0.17
    _health
    0.16
     Health
    0.16
    Activations Density 0.159%

    No Known Activations