© 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. 36314
    Prev
    Next
    INDEX
    Explanations

    healing and recovery

    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
    饮水
    -0.10
     Registrar
    -0.09
    梦幻
    -0.09
    æĻ¨
    -0.08
    asto
    -0.08
    eus
    -0.08
    è´Ł
    -0.08
    å¿ł
    -0.08
    çĤ«èĢĢ
    -0.08
     inev
    -0.08
    POSITIVE LOGITS
    æģ¢å¤į
    0.20
    çĹĬ
    0.19
     recovery
    0.19
     healing
    0.18
     recuper
    0.17
    康å¤į
    0.17
     Recovery
    0.16
     Healing
    0.15
     healed
    0.15
    recover
    0.15
    Activations Density 0.124%

    No Known Activations